need-reading-material
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to perform deep research into external sources such as articles, blogs, and whitepapers. This creates an inherent surface for indirect prompt injection where instructions embedded in those external sources could attempt to influence the agent's behavior.
- Ingestion points: External web content and documents retrieved during the research process.
- Boundary markers: None specified in the prompt instructions to delimit external content.
- Capability inventory: Implied web browsing and search tool access to fulfill the research request.
- Sanitization: No explicit sanitization or filtering of retrieved content is defined.
- [NO_CODE]: The skill does not include any scripts, binaries, or executable logic, relying solely on natural language instructions and metadata.
Audit Metadata