ClawAudit verdict
skill-provenance
Reads files AND uses eval/Function
This skill implements version tracking conventions for skill bundles using YAML frontmatter and manifest files; it is a documentation and versioning standard with no network calls, credential access, or malicious behavior.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Permission integrity
file_read
Findings (3)
Writes to SKILL.md — self-modifying skill
SKILL.md · code · SKILL.md: Reworked body flow rules and added an optional append
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
References agent configuration files
README.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.
file_readdynamic_eval Thanks — recorded.