domain-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting data from files within the project repository which are considered untrusted sources.
- Ingestion points: The skill reads from CONTEXT.md, CONTEXT-MAP.md, and project source code files to build and sharpen the domain model.
- Boundary markers: No explicit markers or instructions to ignore embedded instructions are provided when processing these files.
- Capability inventory: The skill has the capability to write and modify files (CONTEXT.md and ADRs) based on the processed information.
- Sanitization: No sanitization or validation of the input data from the repository is implemented before it is interpreted by the agent.
Audit Metadata