skills/peterbamuhigire/chwezi-sdlc-documentation/06-saas-onboarding-journey-spec/Gen Agent Trust Hub
06-saas-onboarding-journey-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project documentation (PRDs, research notes, events catalogues) without using boundary markers to separate data from instructions. This creates a surface for indirect prompt injection where malicious content in those files could steer the agent's behavior. However, the impact is limited as the skill does not use high-risk tools like network access or shell execution.\n
- Ingestion points: PRD.md, Pricing_And_Packaging_Spec.md, user-research notes, events catalogue.\n
- Boundary markers: None.\n
- Capability inventory: Restricted to reading and writing markdown files.\n
- Sanitization: None.
Audit Metadata