attribute-driven-design
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external design drivers, including functional requirements and quality-attribute scenarios, which are typically sourced from external documentation. These inputs represent a potential surface for indirect prompt injection if the source materials contain hidden or adversarial instructions.
- Ingestion points: Step 1 involving the collection of design inputs (requirements, scenarios, and constraints) from stakeholder documents.
- Boundary markers: The skill does not explicitly define markers to isolate external requirement text from the agent's instructions.
- Capability inventory: The skill's operations are limited to logic, design decomposition, and documentation. No dangerous capabilities such as network access, arbitrary command execution, or sensitive file system access are identified.
- Sanitization: While the skill includes guardrails to ensure drivers are sourced from specific documents and prevents the agent from inventing tactics, it lacks explicit sanitization for potential injection strings within the requirements themselves.
Audit Metadata