cypress-debugger

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses node -e to run local JavaScript snippets for parsing JSON and XML report files.
  • [COMMAND_EXECUTION]: Employs standard Unix utilities like find, cat, and jq to locate and extract failure details from the local filesystem.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
  • Ingestion points: Reads contents from cypress/reports/mochawesome.json and cypress/reports/results.xml.
  • Boundary markers: None; extracted data is presented directly to the agent without delimiters.
  • Capability inventory: Includes filesystem navigation and local code execution capabilities.
  • Sanitization: None; error messages and stack traces are processed without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:16 AM