research
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs an agent to research external primary sources including documentation and source code, which are untrusted inputs.
- Ingestion points:
SKILL.mdspecifies reading official docs, source code, specs, and APIs. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions found within the researched content.
- Capability inventory: The skill involves writing findings to a file in the repository.
- Sanitization: No sanitization or validation of the retrieved content is described before it is processed and stored in the repository.
Audit Metadata