research
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions are limited to research and documentation tasks. The agent is directed to use primary sources and maintain repository conventions, which is standard behavior for a documentation agent.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads from external sources and writes to the repository. This is inherent to the research task and the capability is restricted to writing Markdown files.
- Ingestion points: External documentation, source code, and APIs (SKILL.md).
- Boundary markers: None specified in the instructions.
- Capability inventory: The agent can write Markdown files to the repository (SKILL.md).
- Sanitization: No explicit content sanitization is described for the gathered data.
- [NO_CODE]: No executable scripts or binary files were found in the skill package.
Audit Metadata