frontend-component-build
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional Markdown documentation and reference templates. It does not include any executable scripts (.js, .py, .sh), binaries, or automated configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a code refactoring assistant, which involves processing untrusted source code or design specifications provided by users.
- Ingestion points: The skill triggers on user-provided component code for refactoring and design specifications for new implementations (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to separate user-provided code from the agent's instructions.
- Capability inventory: The skill utilizes the agent's core code generation and modification capabilities to output new or refactored component code (SKILL.md).
- Sanitization: There are no explicit instructions for sanitizing or validating the input source code provided by the user.
Audit Metadata