domain-modeling
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided domain terminology and project documentation, which constitutes an attack surface for indirect prompt injection. The risk is low as the functionality is limited to generating documentation.
- Ingestion points: The skill reads from user input and existing markdown files in
docs/adr/andskills/internal/project-context/. - Boundary markers: The instructions do not specify delimiters to isolate user-supplied terms from the agent's internal logic.
- Capability inventory: The skill utilizes file read and write operations to manage project documentation files.
- Sanitization: The instructions do not define specific sanitization or validation steps for the content of the domain terms or decisions before they are written to the filesystem.
Audit Metadata