domains / families / general / yao-doctor

yao-doctor

separate

Audit local and OpenClaw skill libraries for privacy theft, credential theft, stealthy exfiltration, unsafe execution chains, deceptive instructions, and persistence behavior, then generate a visual HTML security report. Use when Codex needs to security-review one skill or a full skill library before install, enablement, or execution. Do not use for generic cleanup, usage estimation, or app-level security review outside skill packages.

When to use

• security-review one skill
• security-review a full skill library
• audit skill packages as untrusted code
• audit untrusted instructions
• scan for privacy theft
• scan for credential theft
• scan for stealthy exfiltration
• scan for unsafe execution chains

When not to use

• generic code security reviews outside skill folders
• skill cleanup
• archival
• deduplication
• stale-usage analysis
• privacy policy writing without scanning files
• creating a brand-new skill with no security audit need
• app-level security review outside skill packages

Skill page

Source