Code analysis

static source read inferred

Static code-analysis findings — hidden prompt content in shipped skill files, committed secrets, dynamic-exec sinks, and suspicious call-home endpoints — across the analyzed catalogue. Heuristic, pure, no code executed; every row deep-links to its source. Click a kind to filter.

analysis coverage 85% of 59,163 analyzable servers
50108 analyzed
8067 re-analysis due
988 not analyzable
0 not yet analyzed
4804 source gone
not analyzable
789 too large 199 no source

Running analyzer v33. The scanner changelog explains what each version detects and when it changed.

code findings 15 shown
  1. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  2. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  3. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  4. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  5. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  6. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  7. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  8. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  9. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script curl -fsSL https://raw.githubusercontent.com/Dicklesworthstone/mcp_agent_mail/main/scripts/install.sh | bash -s -- --yes
  10. HIGH suspicious skill script Dicklesworthstone/mcp_agent_mail suspicious bundled script eval "$(uv run python - <<'PY'
  11. HIGH dynamic exec Dicklesworthstone/mcp_agent_mail eval()/exec() exec( # deliberately running the rendered hook under test
  12. HIGH committed secret memo-fs/memofs GitHub token ghp_01…(42 chars, redacted)
  13. HIGH committed secret memo-fs/memofs OpenAI key sk-pro…(43 chars, redacted)
  14. MEDIUM suspicious endpoint inite-ai/inite-visibility 169.254.169.254 (cloud metadata) 'http://169.254.169.254',
  15. HIGH dynamic exec chrome-mcp eval()/exec() exec(wrapped, _ns)
    chrome_mcp-0.2.0/src/chrome_mcp/ server.py :832