domain-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where untrusted user input (domain terms, definitions, and scenario descriptions) is ingested and subsequently written to persistent project files.
- Ingestion points: User interactions regarding domain terminology and decisions described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential injections within the user-provided definitions.
- Capability inventory: The agent is instructed to write to
CONTEXT.mdand create/update markdown files indocs/adr/. - Sanitization: No explicit sanitization or validation of the user-provided strings is mentioned before they are appended to project documentation.
Audit Metadata