Caveat verdict

agnt-data

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

Accesses credentials AND makes external network calls

The skill accesses a unified social data API, which requires an API key. It provides a clear and transparent approach to using this API.

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.

50
security
90
transparency
90
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Findings (1)

Pattern match high

Instructs covert action — may act without user awareness

references/facebook/README.md · code · silently

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: AGNTDATA_API_KEY). Requires 1 system binary. (1 elevated: curl).

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