Caveat verdict
cubistic-bot-runner
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Runs a proof-of-work pixel-painting bot against the Cubistic game backend using a user-supplied API key and backend URL; the skill explicitly states the key should only go to the Cubistic backend and implements polite rate-limiting behavior.
⚠ 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.
70
security
60
transparency
70
maintenance
Findings (1)
Pattern match critical
Possible hardcoded credential
SKILL.md · code · API_KEY="my-bot-id
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.