docs
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation and code comments from external sources, creating a potential surface for indirect injection.
- Ingestion points: The skill reads existing documentation and code comments from the specified component (SKILL.md).
- Boundary markers: There are no instructions defining delimiters or markers to separate untrusted data from the agent's instructions.
- Capability inventory: This skill provides instructions for generating documentation and does not include scripts, network operations, or shell commands.
- Sanitization: No sanitization or filtering logic is provided for the content read from external files.
Audit Metadata