watsa-insurance-float
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 data, market themes, and portfolio context, which constitutes an ingestion surface for potential indirect prompt injection.
- Ingestion points: Data enters the context through user-provided financial and market data as specified in the inputs section of SKILL.md and the data requirements in invest.md.
- Boundary markers: The instructions lack specific delimiters or explicit instructions for the agent to ignore or isolate potentially malicious instructions embedded within the ingested financial data.
- Capability inventory: The skill does not possess capabilities for network communication, file system modification, or shell command execution, which effectively negates the operational risk of an injection attack.
- Sanitization: There are no defined mechanisms for filtering or sanitizing the input data within the provided skill instructions.
Audit Metadata