Skills/PyPI/mcp-standards

mcp-standards@0.1.0a2

CAUTION· static only

Publisher claims: "Self-learning AI standards system - learns from corrections and auto-updates CLAUDE.md" Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher airmcp-com · publishing for 395 daysInstalls 25Last detonated 5d ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
GEMINI_API_KEYConfiguration, not credentials: COST_OPTIMIZATION, DEFAULT_MODEL, FALLBACK_MODEL
Where it talks to
no vendor host named in the codeAlso airmcp.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

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 analysed it statically (a sandbox run is pending) on 2026-11-09 and scored it 53/100 (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 file system command detected; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
npx invocation of non-well-known package.claude/helpers/github-setup.sh:27 · npx invocation of non-well-known package — may execute untrusted codeecho " - npx claude-flow pr enhance"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/commands/hooks/setup.md:21 · npx invocation of non-well-known package — may execute untrusted codenpx claude-flow hook session-end --summaryFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detected.claude/settings.json:34 · Destructive file system command detected"Bash(rm -rf /)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known package.claude/helpers/github-setup.sh:26 · npx invocation of non-well-known package — may execute untrusted codeecho " - npx claude-flow repo analyze"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file paths.claude/commands/hooks/setup.md:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file": ".env.production",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known package.claude/helpers/quick-start.sh:14 · npx invocation of non-well-known package — may execute untrusted codeecho " npx claude-flow task orchestrate --task "Build REST API""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/helpers/quick-start.sh:8 · npx invocation of non-well-known package — may execute untrusted codeecho " npx claude-flow swarm init --topology hierarchical"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_standards/hooks/significance_scorer.py:58 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env": 0.7,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known package.claude/settings.json:12 · npx invocation of non-well-known package — may execute untrusted code"Bash(npx claude-flow:*)",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/commands/hooks/setup.md:7 · npx invocation of non-well-known package — may execute untrusted codenpx claude-flow init --hooksFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/helpers/github-setup.sh:28 · npx invocation of non-well-known package — may execute untrusted codeecho " - npx claude-flow issue triage"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/helpers/quick-start.sh:17 · npx invocation of non-well-known package — may execute untrusted codeecho " npx claude-flow swarm monitor"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/helpers/github-setup.sh:25 · npx invocation of non-well-known package — may execute untrusted codeecho " - npx claude-flow github swarm"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/commands/hooks/setup.md:36 · npx invocation of non-well-known package — may execute untrusted code"command": "npx claude-flow hook pre-write --file '${tool.params.file_path}'"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/helpers/quick-start.sh:11 · npx invocation of non-well-known package — may execute untrusted codeecho " npx claude-flow agent spawn --type coder --name "API Developer""Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_standards/autolog.py:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env": 0.7,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known package.claude/helpers/setup-mcp.sh:15 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add claude-flow npx claude-flow mcp startFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/commands/hooks/setup.md:18 · npx invocation of non-well-known package — may execute untrusted codenpx claude-flow hook pre-edit --file test.jsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/settings.json:44 · npx invocation of non-well-known package — may execute untrusted code"command": "cat | jq -r '.tool_input.command // empty' | tr '\\n' '\\0' | xargs -0 -I {} npx claude-flow@alpha hooks pre-command --command '{}' --validate-safety true --prepare-resources true"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/commands/hooks/setup.md:75 · npx invocation of non-well-known package — may execute untrusted codenpx claude-flow hook pre-edit --file app.js --debugFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/INTEGRATION_GUIDE.md:122 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file4. **Auto-update triggered**: `./CLAUDE.md` updated automaticallyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/mcp_standards/server.py:228 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filedescription="Update CLAUDE.md file with learned preferences (creates backup first)",Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/INTEGRATION_GUIDE.md:52 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file✅ **Auto-Update CLAUDE.md**: Config files updated intelligentlyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:340 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file4. **Update CLAUDE.md** when confidence scores are high (0.7+)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:364 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file4. **Update CLAUDE.md** when confidence scores are high (0.7+)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/guides/QUICKSTART.md:57 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// → CLAUDE.md will updateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detectedtests/conftest.py:123 · Destructive file system command detected"command_injection": "; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:382 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileUser Correction → Pattern Extraction → Frequency Tracking → Confidence Scoring → Preference Promotion → CLAUDE.md UpdateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Pipe-to-shell pattern.github/workflows/ci.yml:26 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:328 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file6. Run `suggest_claudemd_update()` → Get suggestion to add to CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known package.claude/settings.json:53 · npx invocation of non-well-known package — may execute untrusted code…input.file_path // .tool_input.path // empty' | tr '\\n' '\\0' | xargs -0 -I {} npx claude-flow@alpha hooks pre-edit --file '{}' --auto-assign-agents true --load-context true" …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:61 · npx invocation of non-well-known package — may execute untrusted code- `npx claude-flow sparc batch <modes> "<task>"` - Parallel executionFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/mcp_standards/intelligence/claudemd_manager.py:238 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileUpdate CLAUDE.md file with learned preferencesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/SELF-LEARNING-PRD.md:270 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file├─ Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:55 · npx invocation of non-well-known package — may execute untrusted code- `npx claude-flow sparc modes` - List available modesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.claude/settings.json:64 · npx invocation of non-well-known package — may execute untrusted code"command": "cat | jq -r '.tool_input.command // empty' | tr '\\n' '\\0' | xargs -0 -I {} npx claude-flow@alpha hooks post-command --command '{}' --track-metrics true --store-results true"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shell.github/workflows/ci.yml:87 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:56 · npx invocation of non-well-known package — may execute untrusted code- `npx claude-flow sparc run <mode> "<task>"` - Execute specific modeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shell.github/workflows/ci.yml:26 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/mcp_standards/server.py:602 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"""Update CLAUDE.md file with learned preferences"""Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesPKG-INFO:352 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file6. Run `suggest_claudemd_update()` → Get suggestion to add to CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/conftest.py:120 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"path_traversal": "../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/SELF-LEARNING-PRD.md:256 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileIf pattern repeats 3+: Update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:57 · npx invocation of non-well-known package — may execute untrusted code- `npx claude-flow sparc tdd "<feature>"` - Run complete TDD workflowFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesREADME.md:358 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileUser Correction → Pattern Extraction → Frequency Tracking → Confidence Scoring → Preference Promotion → CLAUDE.md UpdateFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/mcp_standards/server.py:594 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file"message": f"Found {len(suggestions)} suggestion(s) for CLAUDE.md update"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/mcp_standards/hooks/capture_hook.py:8 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file3. Update CLAUDE.md filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Pipe-to-shell pattern.github/workflows/ci.yml:87 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/CONFIG_STANDARDS.md:372 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- Primary updates: Always update CLAUDE.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageCLAUDE.md:58 · npx invocation of non-well-known package — may execute untrusted code- `npx claude-flow sparc info <mode>` - Get mode detailsFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filesdocs/INTEGRATION_GUIDE.md:549 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file**Before**: Manually edit CLAUDE.md after correctionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known package.claude/settings.json:73 · npx invocation of non-well-known package — may execute untrusted code"command": "cat | jq -r '.tool_input.file_path // .tool_input.path // empty' | tr '\\n' '\\0' | xargs -0 -I {} npx claude-flow@alpha hooks post-edit --file '{}' --format true --update-memory true"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive command against a filesystem root or devicetests/conftest.py:123 · Destructive command against a filesystem root or device"command_injection": "; rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,327 tok
2 files · 81 in bundle

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

Known vulnerabilities

No advisories in OSV for mcp-standards@0.1.0a2 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim airmcp-com: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. 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.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Pipe-to-shell pattern≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Remote installer piped to shell≈ +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 airmcp-comPropose a patch to the maintainer