ClawAudit verdict
ecommerce-seller-info
ecommerce-seller-info-skill
The pattern `eval "$(python scripts/extract-seller.py)"` executes arbitrary shell output from a Python script, which is a broad execution sink; while the stated purpose is legitimate DOM scraping, this pattern could execute unexpected commands if the script is tampered with.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (1)
References agent memory files
SKILL.md ยท prose ยท downgraded ยท memory.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
dynamic_eval Is this flag fair?
Thanks โ recorded.