quiver
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents an indirect prompt injection surface because it fetches data from an external source (Quiver Quantitative API) and returns it directly to the agent.
- Ingestion points: Data is ingested via the
quiverquantlibrary inscripts/query_quiver.py(e.g.,quiver.congress_trading(),quiver.lobbying()). - Boundary markers: The output is provided as a raw JSON array without explicit delimiters or warnings to ignore embedded instructions.
- Capability inventory: The script itself is limited to network requests and standard output; it does not contain file-system write operations or arbitrary shell execution capabilities.
- Sanitization: No sanitization or filtering is performed on the data returned by the API before it is passed to the agent.
- [EXTERNAL_DOWNLOADS]: The skill relies on the
quiverquantPython library to communicate with the Quiver Quantitative API. This is a standard and expected dependency for the skill's primary purpose.
Audit Metadata