automation-debug-tests

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses framework-native CLI tools via npx to execute tests and view trace files (e.g., npx playwright test, npx codeceptjs run). These operations are consistent with the skill's stated purpose of debugging automated tests and involve trusted, well-known industry tools.
  • [SAFE]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from the application under test (DOM fragments via outerHTML, console logs, and network request failures). However, this data ingestion is restricted to diagnostic purposes.
  • Ingestion points: DOM state capture (page.locator().evaluate()), console message monitoring, and network failure logs.
  • Boundary markers: Not explicitly defined for separating application output from agent instructions.
  • Capability inventory: Shell command execution via npx and browser-side script execution.
  • Sanitization: No explicit sanitization or filtering of application logs or DOM content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 11:18 PM
Security Audit — agent-trust-hub — automation-debug-tests