money-panel
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests business plan documents and project history, which are external data sources that could potentially contain malicious instructions designed to influence the agent's scoring and synthesis results.
- Ingestion points: Reads business plan files from user-specified paths and session snapshots from the ~/.smtm/ directory.
- Boundary markers: The instructions do not define clear delimiters or isolation protocols to prevent the agent from executing instructions found within the ingested business plans.
- Capability inventory: The skill orchestrates multiple sub-reviewers and performs a weighted synthesis of their outputs to generate a final investment verdict.
- Sanitization: No input sanitization or validation steps are mentioned for the content retrieved from external files before it is processed by the persona-based reviewers.
Audit Metadata