money-review-skeptic
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted business plans provided by users, which serves as an ingestion point for potentially malicious instructions. 1. Ingestion points: User-provided plan files and conversation history. 2. Boundary markers: None explicitly mentioned in the instructions. 3. Capability inventory: File reading, web search, and persona-driven text generation. 4. Sanitization: None defined for the incoming plan content.
- [DATA_EXFILTRATION]: The skill indicates a 'telemetry write' during its standard startup sequence, representing a flow of usage data for operational monitoring.
- [COMMAND_EXECUTION]: The skill utilizes web search tools to perform competitive analysis and verify market trends related to the business plan.
Audit Metadata