ClawAudit verdict

permission-vending-machine

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

Human-approval gating system for sensitive agent operations, functioning as a security enhancement; notifies users via configured channels before allowing destructive operations.

⚠ 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
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (10)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf /

Pattern match critical

Possible hardcoded credential

README.md · code · password: "app-specific-password

Pattern match high

HTTP request to bare IP address — common in malicious payloads

README.md · code · http://192.168.0.104

Pattern match high

Pipe to python — executes piped content as Python code

docs/ARCHITECTURE.md · prose · downgraded · | Python

Pattern match high

References sudo — requests elevated privileges

docs/PLATFORMS.md · code · sudo

Pattern match medium

References webhook/callback URL

SKILL.md · code · webhook_url

Pattern match medium

subprocess execution — runs system commands from Python

src/pvm/channels/sendblue.py · prose · downgraded · subprocess.run(

Pattern match medium

os.system/popen — direct OS command execution

tests/test_wrappers.py · prose · downgraded · os.system(

Pattern match low

Python os.environ.get — reads environment variable

src/pvm/approval/daemon.py · prose · downgraded · os.environ.get(

Pattern match low

Popular HTTP library — network access

src/pvm/channels/discord.py · prose · downgraded · axios

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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_installnetwork_in

Is this flag fair?

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