Caveat verdict

agent-browser

agent-browser-vercel

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

Encodes data AND uses eval

Browser automation CLI with the same command patterns as agent-browser-4; behavior is entirely consistent with the stated web automation purpose and no malicious patterns are present.

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
80
transparency
70
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

Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)

LLM05 · ASI05 · ASI10

Findings (1)

Pattern match medium

Opens WebSocket connection

references/commands.md · code · WebSocket

Permissions & capabilities

No declared permissions — minimal attack surface.

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