domain-modeling
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code and documentation, which could allow instructions embedded in the repository to influence the agent's behavior during domain modeling tasks.
- Ingestion points: Reads
CONTEXT.md,CONTEXT-MAP.md,docs/adr/*.md, and project source code from the repository. - Boundary markers: No specific delimiters or safety instructions are defined for the agent when reading or processing these files.
- Capability inventory: The skill is authorized to create and update architectural documentation and glossary files within the project.
- Sanitization: The skill does not explicitly describe any methods for validating or sanitizing the content it reads before using it to update repository files.
Audit Metadata