experience-ui-bundle-frontend-generate
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local utility scripts (
resolve-ui-bundle.mjs,check-preconditions.mjs,verify-rules.mjs) usingnode. These scripts facilitate project discovery and enforce configuration rules by inspecting the local filesystem and file contents to ensure the bundle is correctly scaffolded and free of forbidden patterns. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation and modification of application source files (React components, route definitions, and HTML) based on natural language user requests. This process interpolates user-provided text into the project's codebase, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: User prompts defining new pages, component logic, and branding text (e.g., app name, labels).
- Boundary markers: No specific delimiters or safety warnings for user-provided content are implemented in the file generation templates.
- Capability inventory: Filesystem write access for source code generation and execution of local validation and build scripts.
- Sanitization: The
verify-rules.mjsscript performs pattern-based validation of imports and boilerplate but does not provide comprehensive sanitization of user-injected strings against malicious instructions.
Audit Metadata