domain-modeling
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for architectural documentation and glossary management. It operates by reading and writing local Markdown files such as CONTEXT.md and ADR files to maintain project alignment.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from the codebase. 1. Ingestion points: The skill reads the project's source code files during the cross-reference step and processes user-provided scenarios in SKILL.md. 2. Boundary markers: The instructions do not define clear delimiters or markers to separate instructions from the data being analyzed. 3. Capability inventory: The skill is limited to reading repository files and writing Markdown documentation. It lacks access to network tools, shell execution, or sensitive environment variables. 4. Sanitization: There are no documented mechanisms for sanitizing or escaping content read from the codebase before it is processed by the agent.
Audit Metadata