meta-bankability-scoring
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided business plans, which constitute untrusted external data that could contain malicious instructions.
- Ingestion points: The agent is instructed to read full plan sections, financial models, and appendix documents (SKILL.md, Required Inputs).
- Boundary markers: There are no explicit delimiters or instructions defined to prevent the agent from obeying commands embedded within the business plan content.
- Capability inventory: The skill is limited to analytical reasoning and text generation; it does not utilize shell execution, file writing, or network communication tools.
- Sanitization: The skill does not perform any validation or sanitization of the plan content before processing it.
- Risk Assessment: Because the skill lacks dangerous capabilities, the risk of an indirect prompt injection resulting in system compromise is negligible.
Audit Metadata