evidence-based-citations
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill instructs the agent to fetch content from external web pages to provide verifiable quotes for citations. This network activity is the primary intended function of the skill and is triggered only when verification is requested.
- [INDIRECT_PROMPT_INJECTION]: By processing content from external websites, the skill exposes an indirect prompt injection surface. However, the risk is mitigated by the skill's instructions to provide exact verbatim quotes and its strict output structure, which limits the potential for external content to override agent instructions.
Audit Metadata