workflow-spec-to-mockup

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts and tools for workflow maintenance and output verification. Specifically, it calls node .claude/scripts/lib/workflow-skill-contract.cjs --write to update internal documentation blocks and html-export --to=png to generate visual evidence of the created mockups.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external 'canonical specs' which represent an untrusted data ingestion surface. Maliciously crafted instructions within these specs could potentially influence the agent's behavior during the design and mockup generation phases.
  • Ingestion points: Technical specifications typically located in the docs/specs directory.
  • Boundary markers: The skill uses explicit frontmatter keys (design_spec:, mockup:) to link artifacts and instructs the agent to leave the spec body untouched.
  • Capability inventory: The agent is authorized to write to tmp/ and team-artifacts/ directories, spawn subagents for delegated tasks, and execute local rendering commands.
  • Sanitization: The workflow incorporates multiple 'Quality Gates' (UX-1 through UX-11) and manual review points (e.g., $ui-design --mode=review) to validate output before finalization.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:16 PM