ClawAudit verdict
Agent Browser
agent-browser-conflict
18
🔴 Dangerous
High-risk patterns flagged for review — automated deep scan, not behaviorally verified.
The skill provides browser automation, but uses dynamic_eval and package_install, which poses a high risk.
⚠ 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.
90
security
70
transparency
70
maintenance
Permission integrity
Installs packages at runtime — transitive dependencies are not auditable
package_install
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
Requires 2 system binaries. (1 elevated: npm).
package_installdynamic_eval Is this flag fair?
Thanks — recorded.