frontend-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and project configuration files (e.g., package.json, tsconfig.json) to provide engineering guidance. This represents a standard indirect injection surface for an AI-based coding assistant.
- Ingestion points: Processes frontend source files (.tsx, .jsx, .vue, .svelte) and build configuration files.
- Boundary markers: The skill does not explicitly use delimiters or instruction-bypass warnings when reading external file content.
- Capability inventory: The skill allows the agent to read, edit, and write files, as well as execute grep commands via Bash.
- Sanitization: No explicit sanitization or validation of the content of the ingested project files is performed before they are used to influence the agent's output.
Audit Metadata