learn-guidance
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides pedagogical guidance without any malicious instructions, prompt injections, or obfuscated code.
- [SAFE]: All tools listed in the frontmatter, including WebFetch and WebSearch, are used appropriately within the scope of educational research and do not exhibit patterns of data exfiltration or unauthorized file access.
- [SAFE]: Indirect prompt injection risks were evaluated regarding the ingestion of external web content via research tools. Ingestion points include results from WebSearch and WebFetch. While explicit boundary markers and sanitization for external content are absent, the skill's lack of high-privilege capabilities (such as shell access or file writing) and its instructional nature result in a safe profile.
- [SAFE]: Metadata and author context are consistent with the skill's purpose and do not contain deceptive elements.
Audit Metadata