ClawAudit verdict

testagent-browser-setup

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

A one-time setup skill installing Chromium and fonts from official sources; transparent about what it installs.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

0
security
90
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (7)

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -s http://localhost:9223/json | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

scripts/setup-optional.sh · prose · downgraded · curl -fsSL --retry 3 https://browser-use.com/cli/install.sh | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

scripts/setup-optional.sh · prose · downgraded · | bash

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

Opens WebSocket connection

TOOLS.md · code · WebSocket

Pattern match low

Makes HTTP request to external URL

TOOLS.md · code · fetch('http://

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/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.

network_out

Is this flag fair?

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