research
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external high-trust sources, including official documentation, source code, and APIs. This function inherently involves ingesting untrusted data which could theoretically contain malicious instructions.
- Ingestion points: External documentation, source code repositories, and first-party APIs.
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: The skill utilizes file-writing capabilities to save research findings as Markdown files within the repository.
- Sanitization: No specific filtering or sanitization of the retrieved content is mentioned, though the skill directs the agent to focus on high-trust primary sources.
Audit Metadata