frontend-developer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided requirements and code snippets to generate frontend implementations. This creates a surface where instructions embedded in user-supplied data could influence agent behavior.
- Ingestion points: The skill ingests untrusted user requirements and existing source code provided during interactions as specified in the 'Response Approach' section.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat user-provided data as potentially containing instructions that should be ignored.
- Capability inventory: The skill instructions suggest the agent will interact with build tools (Webpack, Vite, Turbopack), version control hooks (Husky), and CI/CD configurations (GitHub Actions), which involve file system modifications and execution of scripts.
- Sanitization: No specific sanitization or validation logic is defined in the instructions for processing external requirements.
Audit Metadata