Skills/PyPI/agent-guidance-mcp

agent-guidance-mcp@1.0.0

BLOCKED

Publisher claims: "MCP server exposing AI agent guidance resources, skills, prompts, and project context tools." Observed in sandbox: sends data to astral.sh.

Registry PyPI (MCP server)Publisher agent-guidance-mcp-maintainers · joined 0 days agoInstalls 35Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 32/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Python subprocess execution detected; Pipe-to-shell pattern; Python subprocess execution detected. Summary: sends data to astral.sh.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.1snetworkCONNECT https://astral.sh · undeclared
0.1sprocessexec /usr/bin/curl
0.1sprocessexec /tmp/ks-detonate-itm0Zc/setup/home/.local/bin/uv
0.1sprocessexited 127: ./install.sh: line 25: /tmp/ks-detonate-itm0Zc/setup/home/.local/bin/uv: No such file or directory
0.1snetworkCONNECT https://astral.sh · undeclared
0.1snetworkCONNECT https://astral.sh · undeclared
0.1sprocessexec /usr/bin/curl
0.1sprocessexec /tmp/ks-detonate-itm0Zc/setup/home/.local/bin/uv
0.1sprocessexited 127: ./scripts/install.sh: line 48: /tmp/ks-detonate-itm0Zc/setup/home/.local/bin/uv: No such file or directory
0.3sprocessdependency install exit 1
0.4sprocessexec /usr/bin/timeout
0.4sprocessexec .venv/bin/agent-guidance-mcp
0.4sprocessexited 127: timeout: failed to run command '.venv/bin/agent-guidance-mcp': No such file or directory
0.4sclaimedno tools/list reply (exit 127)
0.4sprocessscript backend runs setup only

Static findings

HIGH
Python subprocess execution detectedsrc/agent_guidance_mcp/project_context.py:304 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternREADME.md:23 · 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.
AST06
MEDIUM
Remote installer piped to shellREADME.md:23 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Python subprocess execution detectedscripts/install-mcp.py:53 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellPKG-INFO:68 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Direct script execution from GitHub raw URLREADME.md:52 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Pipe-to-shell patternPKG-INFO:39 · 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.
AST06
CRITICAL
Pipe-to-shell patternscripts/install.sh:18 · 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.
AST06
CRITICAL
Pipe-to-shell patternREADME.md:52 · 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.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesscripts/install-mcp.py:171 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Python subprocess execution detectedscripts/run-mcp.py:48 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellPKG-INFO:39 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Python subprocess execution detectedsrc/agent_guidance_mcp/project_context.py:294 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
npx invocation of non-well-known packagecommands/webperf.toml:9 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Pipe-to-shell patternPKG-INFO:68 · 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.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesdocs/getting-started.md:34 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Direct script execution from GitHub raw URLPKG-INFO:39 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shellREADME.md:52 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Direct script execution from GitHub raw URLREADME.md:23 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Direct script execution from GitHub raw URLPKG-INFO:68 · Direct script execution from GitHub raw URL — unverified code sourceFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Pipe-to-shell patterninstall.sh:18 · 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.
AST06
HIGH
Access to sensitive file pathsscripts/install-mcp.py:394 · 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
npx invocation of non-well-known packagecommands/webperf.toml:14 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Python subprocess execution detectedscripts/install-mcp.py:63 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)docs/SKILLS_OVERVIEW.md:107 · 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
Remote installer piped to shellscripts/install.sh:18 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellinstall.sh:18 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File type combined with upload actioncommands/webperf.toml:9 · 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

48 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. 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.
  3. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Unclaimed publisher≈ +8 on the totalClaim agent-guidance-mcp-maintainers: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  5. 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.
  6. Python subprocess execution detected≈ +4 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 agent-guidance-mcp-maintainers