domain-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration metadata. It does not include any executable scripts (Python, JavaScript, Shell) or compiled binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied terminology and existing project source code to generate and update documentation.
- Ingestion points: Reads user chat input (terms/scenarios) and scans repository files (source code and existing documentation) as described in
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are defined for the data ingestion process.
- Capability inventory: The skill is restricted to reading project files and writing to Markdown files (
CONTEXT.md,CONTEXT-MAP.md, and thedocs/adr/directory). - Sanitization: No explicit sanitization or filtering of external content is performed before updating the documentation files.
Audit Metadata