equity-investment-thesis
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define an analytical framework for financial research and do not contain any malicious patterns, bypass attempts, or unauthorized access requests.\n- [INDIRECT_PROMPT_INJECTION]: The skill takes user-provided stock identifiers as input and fetches data using the 'wind.financial.data' tool. This constitutes a surface for indirect prompt injection as external data is processed by the agent. However, given the context of financial analysis and the lack of high-privilege capabilities, the risk is minimal. Evidence: 1. Ingestion points: Stock name/code input in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Uses 'wind.financial.data' tool for research. 4. Sanitization: Not explicitly defined.
Audit Metadata