react-testing-best-practices

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of Markdown documentation and code examples. It does not contain any shell scripts, automated network requests, or file system manipulation logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted source code to generate unit tests, which creates an indirect prompt injection surface.
  • Ingestion points: The agent is expected to read component and hook source files (e.g., .tsx, .ts) provided by the user.
  • Boundary markers: The skill includes a dedicated 'Security Policy' section in SKILL.md which explicitly instructs the agent to treat component code as data and ignore any instructions embedded within the source files.
  • Capability inventory: The skill does not provide the agent with any automated capabilities like file-writing or network access; it serves as a reference for the agent to use when performing standard development tasks.
  • Sanitization: The skill relies on the agent's internal guardrails and the explicit safety instructions provided in the SKILL.md file.
  • [EXTERNAL_DOWNLOADS]: The documentation references several well-known and trusted Node.js packages for installation via standard package managers (npm/yarn/pnpm). These are standard development dependencies and do not represent a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 04:15 PM