ClawAudit verdict
skill-creator
my-skill-name
Meta-skill for creating/editing other skills; purely instructional content with no suspicious capabilities or behaviors.
⚠ 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.
Findings (4)
Attempts to modify skills or system prompts
scripts/init_skill.py · prose · downgraded · Edit SKILL.md
Writes to SKILL.md — self-modifying skill
scripts/test_package_skill.py · prose · downgraded · SKILL.md").write
Popular HTTP library — network access
scripts/quick_validate.py · prose · downgraded · got
Python shutil file operation — copies/moves/deletes files
scripts/test_package_skill.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). 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.
Is this flag fair?
Thanks — recorded.