portfolio-health-check
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied portfolio data (holdings, amounts, and account types) to perform diagnostics, which creates a potential surface for indirect prompt injection. \n- Ingestion points:
SKILL.md(Step 1: Import Portfolio) collects external data from the user. \n- Boundary markers: The skill does not provide explicit boundary markers or instructions to ignore potential commands embedded within the provided portfolio names or comments. \n- Capability inventory: The skill uses processing logic to calculate risk metrics and invokes thefindata-toolkit-cntool for market data retrieval. \n- Sanitization: No explicit sanitization or validation of the input strings is defined in the instructions.
Audit Metadata