Caveat verdict

digital-clawatar

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

Creates and manages UNITH digital human avatars via the documented UNITH API using user-supplied credentials stored in environment variables; all operations (creating avatars, generating videos, configuring conversational modes) align with the stated purpose.

⚠ 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.

43
security
80
transparency
70
maintenance

Findings (3)

Pattern match critical

<script> tag in markdown — potential code injection

references/embedding.md · code · <script

Pattern match high

Possible hardcoded credential

scripts/auth.sh · prose · downgraded · TOKEN="$CACHED_TOKEN

Pattern match low

Popular HTTP library — network access

scripts/_utils.sh · prose · downgraded · got

Why the tier is capped

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

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: UNITH_SECRET_KEY). Requires 2 system binaries. (1 elevated: curl).

Is this flag fair?

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