skills/peterbamuhigire/chwezi-sdlc-documentation/12-saas-pricing-and-packaging-spec/Gen Agent Trust Hub
12-saas-pricing-and-packaging-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process project-related documents which could be manipulated to include hidden instructions.
- Ingestion points: The skill reads
PRD.md,vision.md, and competitive scans as indicated in the workflow and logic prompt. - Boundary markers: No specific delimiters or instructions (e.g., XML tags or clear 'ignore' prompts) are provided to isolate untrusted document content from the agent's core instructions.
- Capability inventory: The skill writes a
Pricing_And_Packaging_Spec.mdfile and is configured with read/search access to project artifacts. - Sanitization: There is no mechanism described for validating or sanitizing the content of the ingested files prior to processing.
Audit Metadata