ddd-openspec-bridge
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data from DDD modeling artifacts to generate engineering documentation like proposals, design specifications, and tasks. This ingestion of external data represents an indirect prompt injection surface. However, the risk is classified as safe because the skill focus is strictly on documentation formatting and does not invoke executable code, network operations, or sensitive file access.
- Ingestion points: Reads inputs from problem space definitions, subdomain classifications, aggregate directories, and domain interaction definitions (as listed in SKILL.md).
- Boundary markers: The instructions do not define specific boundary delimiters for untrusted input data, relying instead on structural mapping rules.
- Capability inventory: The skill performs markdown generation and structural analysis; it does not utilize subprocess execution, network requests, or dangerous tools.
- Sanitization: No specific input sanitization or verification logic is present to filter instructions that might be embedded in the source modeling data.
Audit Metadata