03-definition-of-ready
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from project documentation to generate its output, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads
projects/<ProjectName>/_context/vision.mdandfeatures.md(as specified inSKILL.mdStep 1 andlogic.promptStep 1) to inform the generation of readiness criteria. - Boundary markers: The instructions do not define delimiters or provide the agent with "ignore embedded instructions" warnings for the content read from these external files.
- Capability inventory: The skill possesses file read access to the project context and file write access to create the
Definition_of_Ready.mddocument. - Sanitization: There is no evidence of content validation, escaping, or filtering for the data ingested from the markdown context files before it is interpolated into the prompt logic.
Audit Metadata