Caveat verdict

route-specialist

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

Receives external input AND uses eval

Task classification and routing skill that uses deterministic rules and LLM calls to direct tasks to specialist prompts; dynamic_eval capability reflects inline Python classification code that is fully visible and scoped to routing logic.

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.

13
security
70
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 critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Capability combination critical

Reads files AND uses eval/Function — may execute locally stored payloads

LLM05 · LLM06 · ASI05

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read

Permissions & capabilities

No declared permissions — minimal attack surface.

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