policy-brief
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to synthesize evidence by fetching external data, which creates a surface for indirect prompt injection.
- Ingestion points: The skill utilizes
WebFetchandWebSearchtools to retrieve external content and interpolates user-supplied data through the$ARGUMENTSvariable inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded in the fetched external content.
- Capability inventory: The skill is configured with access to
Write,Read,Grep,Glob,WebFetch, andWebSearchtools. - Sanitization: The instructions do not specify any validation, filtering, or sanitization mechanisms for the data retrieved from external sources before it is processed.
Audit Metadata