build-product-business-case
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill contains only instructional text for the AI agent to follow when generating business cases.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for processing various organizational data sources which constitutes an attack surface for indirect prompt injection.
- Ingestion points: SKILL.md (BuildBetter Acceleration section) instructs the agent to use account evidence, calls, signals, surveys, projects, and documents.
- Boundary markers: Absent. There are no specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: None. The skill files do not define any shell execution, network operations, or file-writing capabilities.
- Sanitization: Absent. No filtering or validation steps are defined for the ingested data.
Audit Metadata