ClawAudit verdict
twitter-command-center-search-post-interact
AISA-relay Twitter search and posting skill using AISA_API_KEY with explicit guardrails against soliciting passwords or browser cookies.
⚠ 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 (3)
Possible hardcoded credential
references/engage_twitter.md · code · API_KEY="your-key
Python urllib.request — network access
scripts/twitter_client.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/twitter_client.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.