finance
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external financial data, including market news and company profiles, which constitutes an indirect prompt injection surface.
- Ingestion points: Data retrieved from the
v1/markets/newsandv1/markets/stock/modulesendpoints as documented inFinance_API_Doc.md. - Boundary markers: None identified in the instructions to separate external content from agent instructions.
- Capability inventory: The skill facilitates network GET requests via an API gateway to retrieve market intelligence.
- Sanitization: No explicit sanitization or filtering of the retrieved text is described in the documentation.
Audit Metadata