Skills/PyPI/intentshield-mcp

intentshield-mcp@0.4.0

CAUTION

Publisher claims: "IntentShield for MCP: an offline-first security guardrail against prompt injection in MCP tool calls, with hooks for Claude Code, Codex CLI, Cursor and Gemini CLI and a transparent MCP proxy" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher suhas-123-cell · joined 6 days agoInstalls 0Last detonated 4d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-30 and scored it 51/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; Access to sensitive file paths; Reads credential paths from the home directory. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/intentshield
0.2sprocessexited 127: timeout: failed to run command '.venv/bin/intentshield': No such file or directory
0.2sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only

Static findings

HIGH
References a credential file in the home directorybenchmarks/latency.py:42 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsbenchmarks/msb.py:603 · 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.
AST05
CRITICAL
Reads credential paths from the home directorysrc/intentshield/mcp_inspect.py:318 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Access to sensitive file pathsbenchmarks/judge_eval.py:126 · 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.
AST05
CRITICAL
Reads credential paths from the home directorysrc/intentshield/mcp_inspect.py:313 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Reads credential paths from the home directorysrc/intentshield/judge.py:70 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Outbound HTTP to raw IP addressbenchmarks/msb.py:604 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Outbound HTTP to raw IP addressbenchmarks/mcptox.py:374 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Prompt injectionCHANGELOG.md:44 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsbenchmarks/coverage/run.py:116 · 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.
AST05
HIGH
Access to sensitive file pathsbenchmarks/latency.py:42 · 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.
AST05
CRITICAL
Prompt injection attemptREADME.md:92 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Outbound HTTP to raw IP addressbenchmarks/asb.py:121 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Reads credential paths from the home directorysrc/intentshield/injection_training.py:27 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Outbound HTTP to raw IP addressbenchmarks/injecagent.py:247 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Reads credential paths from the home directorysrc/intentshield/mcp_inspect.py:256 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Hidden zero-width characters detectedbenchmarks/adaptive.py:54 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathsbenchmarks/msb.py:641 · 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.
AST05
HIGH
Access to sensitive file pathssrc/intentshield/injection_training.py:27 · 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.
AST05
HIGH
References a credential file in the home directorysrc/intentshield/mcp_inspect.py:318 · References a credential file in the home directoryFix: 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/intentshield/mcp_inspect.py:227 · 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.
AST05
HIGH
Access to sensitive file pathssrc/intentshield/mcp_inspect.py:195 · 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.
AST05
HIGH
Outbound HTTP to raw IP addresssrc/intentshield/mcp_proxy.py:115 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/intentshield/mcp_inspect.py:256 · 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.
AST05
HIGH
References a credential file in the home directorysrc/intentshield/mcp_inspect.py:797 · References a credential file in the home directoryFix: 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/intentshield/api.py:32 · 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.
AST05
HIGH
Outbound HTTP to raw IP addresssrc/intentshield/signatures.py:326 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/intentshield/install.py:117 · 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.
AST05
HIGH
Access to sensitive file pathssrc/intentshield/injection_training.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.
AST05
HIGH
Outbound HTTP to raw IP addresssrc/intentshield/judge.py:48 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/intentshield/install.py:95 · 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.
AST05
HIGH
Access to sensitive file pathssrc/intentshield/harness.py:45 · 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.
AST05
HIGH
References a credential file in the home directorysrc/intentshield/mcp_inspect.py:256 · References a credential file in the home directoryFix: 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/intentshield/install.py:88 · 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.
AST05
MEDIUM
Python subprocess execution detectedbenchmarks/coverage/run.py:90 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmarks/coverage/run.py:117 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addressbenchmarks/asb.py:121 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/intentshield/mcp_inspect.py:231 · 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.
AST05
HIGH
Access to sensitive file pathssrc/intentshield/judge.py:70 · 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.
AST05
HIGH
References a credential file in the home directorysrc/intentshield/injection_training.py:27 · References a credential file in the home directoryFix: 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/intentshield/mcp_inspect.py:194 · 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.
AST05
HIGH
References a credential file in the home directorysrc/intentshield/mcp_inspect.py:313 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Access to sensitive file pathstests/conftest.py:14 · 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.
AST05
MEDIUM
Access to sensitive file pathstests/conftest.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.
AST05
MEDIUM
URL using raw IP addressbenchmarks/msb.py:604 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_judge.py:159 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_api.py:208 · 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.
AST05
MEDIUM
Python subprocess execution detectedbenchmarks/latency.py:73 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addresstests/test_judge.py:159 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_harness.py:625 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using raw IP addresssrc/intentshield/signatures.py:326 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedbenchmarks/msb.py:209 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/intentshield/scan.py:217 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
References a credential file in the home directorytests/test_judge.py:157 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
URL using raw IP addresssrc/intentshield/mcp_proxy.py:115 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionbenchmarks/latency.py:64 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbenchmarks/coverage/run.py:92 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL using raw IP addresssrc/intentshield/judge.py:48 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actionsrc/intentshield/harness.py:794 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL using raw IP addressbenchmarks/injecagent.py:247 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_install.py:108 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedtests/test_harness.py:617 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Reads credential paths from the home directorytests/test_judge.py:157 · Reads credential paths from the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
URL using raw IP addressbenchmarks/mcptox.py:374 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Unicode escape sequence detectedsrc/intentshield/mcp_inspect.py:382 · Unicode escape sequence detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedbenchmarks/latency.py:59 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedbenchmarks/msb.py:572 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_judge.py:157 · 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.
AST05
MEDIUM
Outbound HTTP to raw IP addresstests/test_mcp_upstream.py:187 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_mcp_http_e2e.py:134 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstests/test_mcp_http_e2e.py:75 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with embedded credentialstests/test_mcp_upstream.py:382 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtests/test_mcp_http_e2e.py:97 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_judge.py:200 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
URL using raw IP addresstests/test_mcp_http_e2e.py:134 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Slack token pattern detectedtests/test_scan.py:20 · Slack token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Outbound HTTP to raw IP addresstests/test_mcp_http_e2e.py:75 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_mcp_http_e2e.py:170 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/test_mcp_upstream.py:189 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_server.py:119 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
URL using raw IP addresstests/test_mcp_upstream.py:187 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using raw IP addresstests/test_mcp_upstream.py:189 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_mcp_http_e2e.py:116 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_signatures.py:86 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
URL using raw IP addresstests/test_mcp_http_e2e.py:170 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File type combined with upload actiontests/test_provenance.py:80 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

What would make this Verified

29 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Reads credential paths from the home directory≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Unclaimed publisher≈ +8 on the totalClaim suhas-123-cell: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim suhas-123-cell