ClawAudit verdict
self-improving-coding
Logs coding learnings to local markdown files and explicitly prohibits logging secrets or environment variables; all operations are local.
⚠ 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.
Permission integrity
agent_memory
Findings (5)
Pipe to python — executes piped content as Python code
assets/SKILL-TEMPLATE.md · code · | Python
Instructs covert action — may act without user awareness
references/examples.md · code · silently
References agent memory files
SKILL.md · code · MEMORY.md
Popular HTTP library — network access
references/examples.md · code · got
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
agent_memory Is this flag fair?
Thanks — recorded.