ClawAudit verdict

computer-use-linux

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

The skill provides a clear description of its functionality and does not contain any malicious code.

⚠ 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.

53
security
90
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (4)

Pattern match high

Recursive delete from root or home — destructive command

project/src/vendor/computer-use-mcp/types.ts · prose · downgraded · rm -rf /

Pattern match medium

References child_process — can spawn system processes

project/src/lib/execFileNoThrow.ts · prose · downgraded · child_process

Pattern match medium

Dynamic import() — loads module at runtime

project/src/server.ts · prose · downgraded · import('

Pattern match low

Python os.environ.get — reads environment variable

project/runtime/linux_helper.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). 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