trade-portfolio
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (holdings and investment goals) which is then used as input for
web_searchand reporting. While this constitutes an ingestion surface for potentially untrusted data, the risk is negligible as it follows standard interactive agent behavior. - Ingestion points: User-provided stock tickers, amounts, and investment goals.
- Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: Uses
web_searchto fetch market data. - Sanitization: Relies on the underlying agent's natural language processing to interpret tickers and data safely.
Audit Metadata