cypress-debugger

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns were detected. The skill's behavior is consistent with its stated purpose of debugging local test failures.
  • [PROMPT_INJECTION]: The skill processes external data from Cypress reports (mochawesome.json and results.xml), which introduces a potential surface for indirect prompt injection. Ingestion points: Local paths in cypress/reports/. Boundary markers: Absent. Capability inventory: Uses find, cat, jq, and node -e for data extraction and analysis. Sanitization: None. This surface is considered safe as it is necessary for the skill's functionality and restricted to the user's local environment.
  • [COMMAND_EXECUTION]: The skill uses Node.js to execute fixed, inline scripts for parsing report data. This is a controlled use of dynamic execution for local data processing and does not pose a remote code execution risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:31 PM