product-design
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data such as design intents, feature definitions, and PRDs to coordinate multi-stage design actions.
- Ingestion points: Processes user design intent and feature definitions to create design task contracts as described in SKILL.md and references/workflow.md.
- Boundary markers: The workflow utilizes explicit design task contracts (design-task-contract.md) and distinct approval gates (Stage 7) to isolate and verify design decisions.
- Capability inventory: The skill functions as a high-level orchestrator and router; no direct shell command execution, file-system writes, or network operations were found in the skill's instructions.
- Sanitization: Relies on manual human review checkpoints and consistency checks via design-guard rather than programmatic input sanitization.
Audit Metadata