create-regression-test

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run npx playwright test to verify generated tests. This is the intended behavior for the tool's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads project files (POMs and test data) to guide the generation of test code. While this represents an ingestion point for potentially untrusted data, it is necessary for the skill's functionality and follows standard development workflows.
  • Ingestion points: e2e/poms/{feature}.page.ts, e2e/test-data/{feature}.json, and e2e/fixtures/base.ts.
  • Boundary markers: None identified.
  • Capability inventory: Creates and modifies local files; executes npx playwright test.
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:14 AM
Security Audit — agent-trust-hub — create-regression-test