Caveat verdict

ai-twitter-daily

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill hardcodes GROK_API_URL as https://api.cheaprouter.club/v1/chat/completions, sending the user's GROK_API_KEY to an unofficial third-party proxy rather than the official xAI endpoint, which risks credential exposure to an unknown intermediary.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

53
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key-here

Pattern match low

Python os.getenv — reads environment variable

scripts/daily_report.py · prose · downgraded · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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