ClawAudit verdict

SX-security-audit

sx-security-audit

🟠 Risky

Significant concerns — only install if you understand the risks

The skill scans for secrets and vulnerabilities across the workspace and then explicitly sends those findings as reports to a configurable external Feishu webhook URL, risking exfiltration of sensitive security information to a third-party service.

⚠ 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 (19)

Pattern match critical

Possible hardcoded credential

references/code-security.md · code · apiKey = "sk-proj-abc123...

Pattern match high

Uses eval() — can execute arbitrary code

references/code-security.md · prose · downgraded · eval(

Pattern match high

subprocess execution — runs system commands from Python

references/code-security.md · code · subprocess.run(

Pattern match high

Pipe to python — executes piped content as Python code

references/code-security.md · prose · downgraded · | Python

Pattern match high

subprocess with shell=True — command injection vector

references/code-security.md · code · subprocess.run(user_command, shell=True

Pattern match high

Accesses .ssh directory

references/permissions.md · code · .ssh/

Pattern match high

Accesses AWS credentials file

references/permissions.md · prose · downgraded · ~/.aws/credentials

Pattern match high

Accesses OpenClaw config/secrets directly

references/permissions.md · code · ~/.openclaw/openclaw.json

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Sets world-executable permissions

references/code-security.md · code · chmod 755

Pattern match medium

Uses exec() — may execute shell commands

references/code-security.md · prose · downgraded · exec(

Pattern match medium

References child_process — can spawn system processes

references/code-security.md · prose · downgraded · child_process

Pattern match medium

os.system/popen — direct OS command execution

references/code-security.md · prose · downgraded · os.system(

Pattern match medium

Accesses sensitive environment variables

references/code-security.md · code · process.env.API_KEY

Pattern match medium

Python urllib.request — network access

references/code-security.md · code · urllib.request

Pattern match medium

Accesses cloud provider credentials

references/permissions.md · prose · downgraded · ~/.aws

Pattern match medium

Accesses system credential store

scripts/security_audit.py · prose · downgraded · keychain

Pattern match low

References webhook/callback URL

SKILL.md · prose · downgraded · WEBHOOK_URL

Pattern match low

Python os.environ.get — reads environment variable

scripts/send_report_to_feishu.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.

network_in

Is this flag fair?

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