create-wiki
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates a workflow for researching technology topics using external tools, creating a surface for indirect prompt injection from untrusted web content.
- Ingestion points: Data retrieved via the
web-researchtool and existing localwiki/files are analyzed during the framing and inventory steps. - Boundary markers: The skill includes instructions to ask the user for clarification when scope or audience is ambiguous and to corroborate risky or ambiguous claims.
- Capability inventory: The skill performs file system write operations to the project's
wiki/directory. - Sanitization: The workflow mandates verifying code and API claims against targeted versions and ensuring documentation remains portable and project-agnostic.
Audit Metadata