ClawAudit verdict

evolving-agent

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

An AI programming coordinator that routes user intents to appropriate sub-modules; data_encoding and agent_memory are used for coordinating sub-agent state and the skill explicitly delegates to documented module files with no evidence of exfiltration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

43
security
80
transparency
70
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (6)

Pattern match critical

Pipe to python — executes piped content as Python code

modules/knowledge-base/agents/summarize-agent.md · code · | python

Pattern match medium

subprocess execution — runs system commands from Python

scripts/core/align_all.py · prose · downgraded · subprocess.run(

Pattern match medium

References sudo — requests elevated privileges

scripts/core/toggle_mode.py · prose · downgraded · sudo

Pattern match low

Python os.environ.get — reads environment variable

scripts/core/path_resolver.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

scripts/github/extract_patterns.py · prose · downgraded · axios

Pattern match low

Python urllib.request — network access

scripts/github/fetch_info.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

data_encodingagent_memory

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API