Caveat verdict

viraloop

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

TikTok/Instagram carousel automation skill using Gemini API and upload-post.com API with documented credentials; autonomous posting is transparently described as the intended design philosophy.

⚠ 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.

68
security
80
transparency
70
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · TOKEN="your-token

Pattern match low

Python os.environ.get — reads environment variable

scripts/generate_image.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 environment variables. (2 sensitive: GEMINI_API_KEY, UPLOADPOST_TOKEN). Requires 3 system binaries.

Is this flag fair?

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