research
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from primary sources like documentation, source code, and APIs, which creates a surface for indirect prompt injection.
- Ingestion points: Official documentation, source code, and first-party APIs accessed during research (SKILL.md).
- Capability inventory: The agent writes research findings to Markdown files in the repository (SKILL.md).
- Boundary markers: Not specified; the instructions do not define delimiters for researched content.
- Sanitization: No explicit instructions are provided for sanitizing or escaping researched content.
Audit Metadata