workflow-design

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided prompts as context for a multi-step design workflow without adequate isolation.
  • Ingestion points: Untrusted user input enters the agent context via the user prompt passed to the /workflow-start design-workflow command in SKILL.md.
  • Boundary markers: Absent. The skill does not use delimiters (such as triple quotes or XML tags) or specific instructions to isolate user input from system commands.
  • Capability inventory: The skill has the capability to trigger a sequence of actions including generating design specifications, creating UI interfaces, and writing frontend code via /design-spec, /interface-design, /frontend-design, and /code-review.
  • Sanitization: There is no evidence of input validation or sanitization of the user-provided context before it is passed to the workflow engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:49 AM