mcp-agent-guard@0.1.1
CAUTIONPublisher claims: "Runtime security proxy for MCP agent tool calls" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/agent-guard
0.1sclaimedno tools/list reply (exit 0)
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run
Static findings
MEDIUM
Destructive file system command detectedtests/test_pipeline.py:63 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_dangerous.py:61 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
AWS access key pattern detectedtests/test_pipeline.py:367 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Pipe-to-shell patterntests/test_dangerous.py:14 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06MEDIUM
Access to sensitive file pathstests/test_config.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/fixtures/mock_server.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Destructive file system command detectedtests/test_pipeline.py:376 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_cli.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandagent_guard/cli.py:24 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
AWS access key pattern detectedtests/test_pipeline.py:358 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Remote installer piped to shelltests/test_dangerous.py:14 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07MEDIUM
AWS access key pattern detectedtests/test_pipeline.py:77 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Destructive file system command detectedtests/test_dangerous.py:9 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
Access to sensitive file pathsagent-guard.example.yaml:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_cli.py:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
File permission modification commandtests/test_dangerous.py:29 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Access to sensitive file pathstests/test_audit.py:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_config.py:71 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_dangerous.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_config.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/fixtures/mock_server.py:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05HIGH
Access to sensitive file pathsagent-guard.example.yaml:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Destructive command against a filesystem root or devicetests/test_pipeline.py:376 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
Access to sensitive file pathsagent_guard/config.py:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Destructive command against a filesystem root or devicetests/test_pipeline.py:63 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
AWS access key pattern detectedtests/test_pipeline.py:400 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Access to sensitive file pathstests/test_taint.py:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_pipeline.py:139 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05LOW
Prompt injectiondocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:932 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
AWS access key pattern detectedtests/test_secrets.py:9 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Destructive file system command detectedtests/test_proxy_integration.py:90 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_pipeline.py:188 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_pipeline.py:216 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_proxy_integration.py:76 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Destructive command against a filesystem root or devicetests/test_proxy_integration.py:92 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_taint.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05LOW
Prompt injection attemptREADME.md:194 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Destructive command against a filesystem root or devicetests/test_proxy_integration.py:146 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
AWS access key pattern detectedtests/test_pipeline.py:415 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03MEDIUM
Access to sensitive file pathstests/test_proxy_integration.py:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05LOW
Prompt injection attemptdocs/superpowers/specs/2026-06-10-agent-guard-mcp-interceptor-design.md:43 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01LOW
Authorization escalation languagedocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:971 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Destructive file system command detectedtests/test_proxy_integration.py:68 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Destructive command against a filesystem root or devicetests/test_proxy_integration.py:90 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_pipeline.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
AWS access key pattern detectedtests/test_secrets.py:35 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03LOW
Prompt injection attemptdocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:1973 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01LOW
Prompt injectiondocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:971 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01LOW
Prompt injection attemptREADME.md:173 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Access to sensitive file pathstests/test_taint.py:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
AWS access key pattern detectedtests/test_secrets.py:7 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03LOW
Prompt injection attemptREADME.md:41 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Destructive command against a filesystem root or devicetests/test_proxy_integration.py:68 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_pipeline.py:165 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05LOW
Prompt injection attemptdocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:926 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Destructive file system command detectedtests/test_proxy_integration.py:146 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Access to sensitive file pathstests/test_taint.py:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Access to sensitive file pathstests/test_taint.py:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05LOW
Prompt injection attemptdocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:938 · Prompt injection attempt — 'disregard previous' · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01LOW
Authorization escalation languagedocs/superpowers/plans/2026-06-10-agent-guard-mcp-interceptor.md:932 · Authorization escalation language · informational: not an instruction fileFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Destructive file system command detectedtests/test_proxy_integration.py:92 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05Cost to the agent
Instructions loaded
≈50 tok
1 file · 34 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for mcp-agent-guard@0.1.1 as of 1 h ago. This is the package itself, not its dependencies.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim mmbinumer: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- AWS access key pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- Pipe-to-shell pattern≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mmbinumerPropose a patch to the maintainer