research
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process external primary sources, which are untrusted data inputs.
- Ingestion points: The agent is directed to read official docs, source code, specs, and first-party APIs (SKILL.md).
- Boundary markers: None are specified to help the agent distinguish between research data and instructional content.
- Capability inventory: The agent has the capability to write research findings to Markdown files within the repository (SKILL.md).
- Sanitization: There are no explicit instructions to sanitize or validate the content retrieved from external sources before saving it to the filesystem.
Audit Metadata