test-all

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Privilege Escalation]: The skill explicitly instructs the agent to launch sub-agents using a "bypassPermissions" mode. This configuration directs the agent to operate outside of standard permission constraints, which is a security consideration regarding the scope of autonomous actions.
  • [Command Execution]: The skill relies on executing several local scripts (e.g., scripts/test-prep.mjs, scripts/test-servers.mjs) and build tools like pnpm and node. This pattern is used for complex orchestration and environment setup, meaning the skill's behavior is dependent on the logic contained within these external script files.
  • [External Downloads]: The skill uses npx playwright install chromium to fetch browser binaries required for testing. These downloads originate from a well-known service (Microsoft/Playwright) and are a standard part of setting up end-to-end testing environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 07:29 PM