macro-liquidity
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to retrieve data from external websites using a search tool, which introduces a vulnerability to indirect prompt injection where malicious content on third-party sites could attempt to influence agent behavior.\n
- Ingestion points: The skill fetches Fed balance sheet data, SOFR rates, bond volatility indices, and exchange rate information from various external web sources as part of its core monitoring function (SKILL.md).\n
- Boundary markers: There are no specific instructions or delimiters defined to isolate the untrusted search results or to warn the agent against following instructions found within those results.\n
- Capability inventory: The skill is primarily focused on data analysis and reporting. It does not possess capabilities for file modification, persistent storage, or outbound network requests beyond the initial data retrieval.\n
- Sanitization: The skill lacks explicit procedures for sanitizing or validating the content retrieved from the web before processing it.
Audit Metadata