research
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from untrusted sources such as third-party documentation and APIs.
- Ingestion points: External official docs, source code, and APIs specified in SKILL.md.
- Boundary markers: None identified.
- Capability inventory: File-write access to the local repository for storing research findings as described in SKILL.md.
- Sanitization: No explicit content validation or sanitization rules are provided for the aggregated content before it is written to the repository.
Audit Metadata