frontend-unit-testing

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill requires the agent to analyze repository files (source code, Python definitions, and demos) to understand component behavior. This creates a surface for indirect prompt injection where malicious content in those files could influence the agent's code generation.\n- Ingestion points: Index.svelte, gradio/components/ source files, and component demo files.\n- Boundary markers: None specified.\n- Capability inventory: The agent is instructed to write test files and execute them using shell commands (pnpm test:run).\n- Sanitization: No explicit instructions for sanitizing or validating the content of the files being researched.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 09:18 AM