search-decisions
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves decision content and rationale from the Jupi platform, which could contain adversarial instructions.
- Ingestion points: Output from
search-decisions-toolandget-decisiontools as described inSKILL.md. - Boundary markers: Absent; the skill does not use delimiters to isolate retrieved data from agent instructions.
- Capability inventory: The skill utilizes tools to read decision data; this external input could potentially influence other tools available to the agent.
- Sanitization: No content filtering or validation is performed on the data fetched from the external source.
Audit Metadata