domain-modeling
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages project documentation like glossaries and ADRs within defined directory structures. It does not perform network operations or access sensitive system files.
- [PROMPT_INJECTION]: The skill analyzes project source code to cross-reference with the domain model. This represents a surface for indirect prompt injection from codebase content. However, the agent's capabilities in this skill are restricted to updating documentation files, which limits the potential impact of such an attack to metadata or glossary corruption.
- Ingestion points: Project source code (
src/) and user dialogue. - Boundary markers: None explicitly defined for code reading.
- Capability inventory: Writing to
CONTEXT.md,CONTEXT-MAP.md, and files withindocs/adr/. - Sanitization: No specific sanitization or filtering of codebase content is mentioned.
Audit Metadata