ClawAudit verdict

browser-use

25
🔴 Dangerous
Multiple critical issues — do not install without thorough manual review

Receives external input AND uses eval

browser-use scores 25/100 (Dangerous). It declares no permissions. Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified). 1 undeclared capability detected — the skill does more than its permissions suggest. 1 high-severity flag.

0
security
50
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

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

LLM01 · LLM05 · ASI01 · ASI05

Capability combination critical

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

LLM05 · ASI05 · ASI10

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

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

No declared permissions — minimal attack surface.

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