frontend-designer

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided design requirements (老合十需求) to generate code and documentation. This is a potential surface for indirect prompt injection if the requirements contain malicious instructions designed to influence the generated code or downstream agent actions.
  • Ingestion points: The input field in the SKILL.md frontmatter specifies '设计需求' (Design requirements) as the primary data source.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially embedded commands within the design requirements.
  • Capability inventory: The skill produces executable React/Vue components, CSS modules, and suggests the execution of local shell scripts (e.g., ./scripts/generate_component.sh).
  • Sanitization: The instructions do not define any validation, filtering, or escaping mechanisms for the input data before it is interpolated into the design output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 04:25 AM
Security Audit — agent-trust-hub — frontend-designer