diataxis
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify user-provided documentation content, which introduces a surface where instructions hidden in that data could influence the agent.
- Ingestion points: User-supplied documentation, README files, or guides provided in the prompt for classification or improvement.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the core skill instructions.
- Capability inventory: The agent is tasked with restructuring, writing, and classifying text based on the provided framework.
- Sanitization: There is no evidence of specific input validation or sanitization for processing external content.
- [SAFE]: The skill incorporates reference material from the official Diátaxis documentation framework (diataxis.fr). These references are informational and derived from a well-known methodology in the technical writing industry.
Audit Metadata