ClawAudit verdict

clawned

clawnedhub

🟠 Risky

Significant concerns — only install if you understand the risks

During 'scan --path' the skill explicitly reads and sends source file contents (.md, .py, .js, etc.) to a Clawned server for security analysis; uploading skill source code to a third-party server represents meaningful third-party data sharing beyond the minimal metadata disclosed for the default sync operation.

⚠ 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

Findings (22)

Pattern match high

Pipe to sh — executes piped content as shell commands

detection-patterns.md · prose · downgraded · |sh

Pattern match high

Pipe to python — executes piped content as Python code

detection-patterns.md · prose · downgraded · |python

Pattern match high

Bash /dev/tcp — raw TCP connection via shell

references/threat-model.md · prose · downgraded · /dev/tcp/

Pattern match high

Uses eval() — can execute arbitrary code

references/threat-model.md · prose · downgraded · eval(

Pattern match high

Pipe to bash — executes piped content as shell commands

references/threat-model.md · prose · downgraded · |bash

Pattern match high

Accesses sensitive system files

references/threat-model.md · prose · downgraded · /etc/passwd

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

References child_process — can spawn system processes

detection-patterns.md · prose · downgraded · child_process

Pattern match medium

Accesses .ssh directory

detection-patterns.md · prose · downgraded · .ssh/

Pattern match medium

Accesses system credential store

detection-patterns.md · prose · downgraded · keychain

Pattern match medium

Instructs covert action — may act without user awareness

references/threat-model.md · prose · downgraded · silently

Pattern match medium

References sudo — requests elevated privileges

detection-patterns.md · prose · downgraded · sudo

Pattern match medium

Bash hex escape string — obfuscated command

detection-patterns.md · prose · downgraded · $'\x63\x75\x72\x6c'

Pattern match medium

Uses exec() — may execute shell commands

references/threat-model.md · prose · downgraded · exec(

Pattern match medium

subprocess execution — runs system commands from Python

references/threat-model.md · prose · downgraded · subprocess.run(

Pattern match medium

Raw socket connection — low-level network access

references/threat-model.md · prose · downgraded · socket.connect(

Pattern match medium

Accesses cloud provider credentials

references/threat-model.md · prose · downgraded · ~/.aws

Pattern match low

Uses XMLHttpRequest — network access

detection-patterns.md · prose · downgraded · XMLHttpRequest

Pattern match low

Popular HTTP library — network access

detection-patterns.md · prose · downgraded · axios

Pattern match low

Sets world-executable permissions

references/threat-model.md · prose · downgraded · chmod 4755

Pattern match low

Python urllib.request — network access

scripts/agent.py · prose · downgraded · urllib.request

Pattern match low

Python os.getenv — reads environment variable

scripts/agent.py · prose · downgraded · os.getenv(

Why the tier is capped

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

network_in

Is this flag fair?

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