event-driven-detector
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's architecture involves processing data from external sources and user queries, which is a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: Corporate event data and financial metrics retrieved via the 'findata-toolkit-cn' tool as mentioned in the Data Enhancement section of SKILL.md.
- Boundary markers: The main workflow instructions do not define explicit delimiters or instructions to disregard potential commands embedded within the retrieved financial data.
- Capability inventory: The skill is limited to data scanning, analysis, and structured reporting; it does not possess autonomous execution capabilities or write access to sensitive system files.
- Sanitization: The instructions focus on analysis logic and do not include specific steps for sanitizing or filtering retrieved content for malicious patterns.
Audit Metadata