playwright-test-generator

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands for code scanning and test runs; it mitigates risk by requiring the agent to display exact command lines and obtain explicit user approval before any execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from web pages and console logs. 1. Ingestion points: Page content, console output, and configuration files (SKILL.md Section 1). 2. Boundary markers: The skill includes explicit instructions to treat external data as untrusted and pastes reference memos into sub-agent prompts. 3. Capability inventory: The skill can write files, execute a local scanner script, and run approved test commands. 4. Sanitization: It uses a mandatory scanner gate to inspect all generated output for security issues before execution (references/execution-and-report.md).
  • [EXTERNAL_DOWNLOADS]: The instructions strictly prohibit commands that perform network downloads, such as npm install, and mandate the --no-install flag for npx to prevent unauthorized software acquisition.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 08:22 AM