writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external markdown files which may contain embedded instructions.
- Ingestion points: User-provided raw material markdown files (SKILL.md).
- Boundary markers: No delimiters are specified to isolate raw content from agent instructions.
- Capability inventory: The agent performs file system read and write operations to generate the article (SKILL.md).
- Sanitization: No explicit sanitization or filtering of input data is mentioned before it is processed by the agent.
Audit Metadata