ClawAudit verdict

agent-browser

agent-browser-5

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Encodes data AND uses eval

Standard browser automation CLI documentation with legitimate web interaction commands and proper guidance on securing auth state files.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

30
security
80
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit 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 (2)

Pattern match high

Accesses shell history/config

references/authentication.md · code · ~/.profile

Pattern match medium

Opens WebSocket connection

SKILL.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