research
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by reading from external primary sources and writing documentation to the local repository.
- Ingestion points: Untrusted external documentation, source code, and first-party APIs as specified in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions are present in the prompt template.
- Capability inventory: The skill can write Markdown files to the local repository (SKILL.md).
- Sanitization: No sanitization or verification process for the ingested content is identified before it is saved to the repo.
Audit Metadata