vet_skill
Runs manifest, static, AST, and dependency scanners on a skill, returning a risk score and per-finding evidence. Use before installing a skill to detect prompt-injection, exfiltration, or security issues.
Instructions
Run all scanners on a single skill — manifest, static patterns, AST, dependencies. Returns a VetReport with risk_score (0-100), risk_level (BLOCK/REVIEW/CAUTION/CLEAN), per-finding details, and a one-paragraph summary. Use this before installing a skill.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| skill_id | Yes | Skill ID to vet. Must exist in the configured backend (default: ~/.openclaw/skills/<skill_id>/). |