skills/peterbamuhigire/business-plan-skills/saas-bankability-and-investor-readiness/Gen Agent Trust Hub
saas-bankability-and-investor-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The workflow requires reading external files including financial projections, cohort models, customer contracts, and data-room exports from the repository as specified in the "Required Inputs" section of SKILL.md.
- Boundary markers: The instructions do not define explicit boundary markers or delimiters to separate the external data from the agent's instructions, nor do they include specific warnings to ignore commands embedded within the data.
- Capability inventory: The skill utilizes the agent's file-reading capabilities to process sensitive data; while it mandates read-only behavior, the surface for data processing remains.
- Sanitization: No sanitization, validation, or filtering mechanisms are prescribed for the ingested financial and legal documents.
Audit Metadata