ClawAudit verdict
amazon-review-workbook
The skill does not exhibit any malicious behavior and is focused on collecting and analyzing Amazon product reviews.
⚠ 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 (5)
Possible hardcoded credential
references/setup.md · code · API_KEY="your-key
Uses eval() — can execute arbitrary code
scripts/amazon_review_workbook.py · prose · downgraded · eval(
Opens WebSocket connection
README.md · code · websocket
HTTP request to bare IP address — common in malicious payloads
scripts/amazon_review_workbook.py · prose · downgraded · http://127.0.0.1
Python os.getenv — reads environment variable
scripts/deeplx_translate.py · prose · downgraded · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.