starting-a-design-plan

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured design orchestration workflow without any indicators of malicious intent or safety bypasses.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted user input and reads a configuration file (.ed3d/design-plan-guidance.md).
  • Ingestion points: User-provided freeform descriptions, external documentation URLs, and the .ed3d/design-plan-guidance.md project file.
  • Boundary markers: None identified. The skill does not use specific delimiters or instructions to ignore embedded commands when processing these inputs.
  • Capability inventory: The skill utilizes TaskCreate, TaskUpdate, and Read tools, and invokes secondary skills for brainstorming and documentation.
  • Sanitization: No explicit sanitization or validation logic is applied to the external inputs before they are incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:38 PM