cathie-wood-innovation
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external financial, market, and structural data. This creates a surface where malicious instructions could be embedded in the processed data to influence the agent's judgment or output.
- Ingestion points: The skill takes "Asset, portfolio, theme, or market context" and "Relevant financial, market, regime, or structural data" as inputs (SKILL.md, invest.md).
- Boundary markers: There are no explicit instructions or delimiters to isolate user-provided data from the agent's instructions or to ignore embedded commands.
- Capability inventory: The skill is primarily intended for generating analysis reports and investment verdicts. No explicit subprocess execution, file writing, or network operations are defined in the provided skill files.
- Sanitization: The instructions do not specify any validation or filtering mechanisms for the external data before it is processed.
Audit Metadata