Caveat verdict

web-access

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

Fetches from network AND uses eval/Function

Browser automation skill using Chrome CDP for legitimate web access tasks; dynamic_eval is via /eval against user-directed pages in the agent's own tabs — no injection or exfiltration.

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
100
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

Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)

LLM05 · LLM06 · ASI05

Findings (2)

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/check-deps.sh · prose · downgraded · http://127.0.0.1

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · WebSocket

Why the tier is capped

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

Permissions & capabilities

Requires 2 system binaries. (1 elevated: curl).

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