frontend-unit-testing
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates browser-based unit testing by downloading browser binaries via
pnpm exec playwright install chromium --only-shell, targeting well-known services. \n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run unit tests (pnpm test:run,vitest run) and manage the test environment. \n- [INDIRECT_PROMPT_INJECTION]: The workflow requires analyzing project source code to generate tests, which presents a surface for potential indirect prompt injection. \n - Ingestion points: Svelte component source files (
Index.svelte), Python component definitions (gradio/components/), and demo files. \n - Boundary markers: The instructions do not define delimiters or warnings to ignore instructions within the ingested source code. \n
- Capability inventory: The agent is authorized to write test files and execute shell commands to run the test suite. \n
- Sanitization: No explicit sanitization or validation of the analyzed project code is mentioned.
Audit Metadata