ClawAudit verdict

amazon

amazon-ordering

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

Browser automation for Amazon ordering and returns using CDP; operates on the user's own logged-in Amazon session with explicit verification steps before purchase, consistent with stated purpose.

⚠ 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.

100
security
100
transparency
90
maintenance

Findings (1)

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("password") and emits it outward ("forward"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · - `agent-browser` CLI installed - Chrome running with `--remote-debugging-port=9222` (see [Starting the browser](#starting-the-browser-if-not-running)) - Logged

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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