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
inputfield 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