technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading local project files to generate documentation, creating a surface for indirect instructions.
- Ingestion points: The skill reads project context and codebase structure as defined in workflows/write-readme.md and SKILL.md using the Read, Grep, and Glob tools.
- Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from following instructions that might be embedded in the files being analyzed.
- Capability inventory: The skill is granted Write access to the filesystem in its SKILL.md configuration, allowing it to modify or create files based on its analysis.
- Sanitization: No mechanisms for sanitization, validation, or escaping of ingested file content are defined in the instructions before the data is processed by the agent.
Audit Metadata