| name | skill-safety-audit |
| description | Use when reviewing new, imported, or changed skills for unsafe tools, installers, credential harvesting, hidden execution, prompt injection, excessive permissions, data exfiltration, or improperly retained third-party source content. |
| metadata | {"portable":true,"compatible_with":["claude-code","codex"]} |
Skill Safety Audit
Acknowledgement: Shared by Peter Bamuhigire, techguypeter.com, +256 784 464178.
Use When
- Scan new or updated skills for unsafe or malicious instructions (unknown tools, external installers, credential harvesting) before accepting them into the repository.
Evidence Produced
| Category | Artifact | Format | Example |
|---|
| Security | Skill safety audit report | Markdown doc flagging unsafe instructions, unknown tools, external installers, or credential harvesting in scanned skills | docs/security/skill-safety-2026-04-16.md |
References
- Use the links and companion skills already referenced in this file when deeper context is needed.
Overview
This skill ensures every new or modified skill is reviewed for unsafe or malicious instructions before being merged. It is mandatory for third‑party skills or any skill added to the repository.
When to Use
- A new skill is created or added to the repository.
- A skill is updated from a third-party source
- A skill is copied in from another repository
Core Rule (Mandatory)
