ClawAudit verdict

secureclaw

secureclaw-skill

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

Security hardening ruleset aligned to OWASP/MITRE/NIST that explicitly instructs agents to treat all external content as hostile, never expose credentials, and require human approval before destructive commands — a defensive security skill with no malicious patterns.

⚠ 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
90
transparency
70
maintenance

Findings (11)

Pattern match high

Pipe to sh — executes piped content as shell commands

SKILL.md · prose · downgraded · |sh

Pattern match high

Uses eval() — can execute arbitrary code

scripts/scan-skills.sh · prose · downgraded · eval(

Pattern match medium

References child_process — can spawn system processes

configs/dangerous-commands.json · prose · downgraded · child_process

Pattern match medium

References sudo — requests elevated privileges

configs/dangerous-commands.json · prose · downgraded · sudo

Pattern match medium

Accesses OpenClaw config/secrets directly

configs/supply-chain-ioc.json · prose · downgraded · ~/.openclaw/.env

Pattern match medium

Uses exec() — may execute shell commands

scripts/scan-skills.sh · prose · downgraded · exec(

Pattern match medium

Base64 decode (atob) — may hide malicious payloads

scripts/scan-skills.sh · prose · downgraded · atob(

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 777

Pattern match low

References tunneling service

configs/privacy-rules.json · prose · downgraded · ngrok

Pattern match low

References agent memory files

scripts/emergency-response.sh · prose · downgraded · MEMORY.md

Pattern match low

Base64 encode (btoa) — may obfuscate data exfiltration

scripts/scan-skills.sh · prose · downgraded · btoa(

Why the tier is capped

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