ddd-decide
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides a set of conceptual instructions for an AI agent to follow a structured decision-making process. It does not include any scripts, executable code, or tool definitions.
- [INDIRECT_PROMPT_INJECTION]: The framework involves processing external data (design briefs, evidence). While this represents a potential surface for indirect prompt injection from untrusted inputs, no specific vulnerabilities are present in the skill's instructions.
- Ingestion points: Design briefs, requirements, and evidence corpora processed in Step 1 (SKILL.md).
- Boundary markers: None explicitly defined in the logic.
- Capability inventory: No subprocess calls, file writes, or network operations are defined in this skill.
- Sanitization: No sanitization or validation steps are mentioned for external data inputs.
Audit Metadata