domain-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by ingesting user-provided terms and existing codebase content to generate or update documentation files such as CONTEXT.md and Architectural Decision Records (ADRs). While this behavior is central to the skill's purpose, it represents a standard vector where malicious data in the input could influence the generated output.
- Ingestion points: Ingests user input during discussion and reads source code for cross-referencing.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as untrusted.
- Capability inventory: The skill is authorized to create and modify markdown files within the repository structure (e.g., /CONTEXT.md, /docs/adr/).
- Sanitization: No specific sanitization or validation logic is defined for the content extracted from the code or user input before writing to files.
Audit Metadata