ClawAudit verdict

steel-browser

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Cloud browser automation via Steel.dev using a user-provided API key; standard web automation skill (navigate, click, screenshot, scrape) through a documented commercial service.

⚠ 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.

security

transparency

maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match critical

Process substitution with source — executes remote content

SKILL.md · code · source <(

Pattern match medium

Uses exec() — may execute shell commands

scripts/_connect.py · prose · downgraded · exec(

Pattern match low

Python os.environ.get — reads environment variable

scripts/_connect.py · prose · downgraded · os.environ.get(

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.

package_install

Is this flag fair?

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