documentation-writer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior or security risks were identified. The skill acts as a technical writer, following established documentation principles and referencing the official Diátaxis framework website.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its ingestion of user-provided markdown files for context.
- Ingestion points: External markdown files provided by the user (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' commands for the provided content.
- Capability inventory: No dangerous capabilities are present; there are no calls for file system writing, network operations, or subprocess execution.
- Sanitization: No specific content filtering or sanitization measures are implemented within the skill instructions.
Audit Metadata