skills/elie222/inbox-zero/qa-run/Gen Agent Trust Hub

qa-run

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes flow specifications from the qa/browser-flows directory. While this constitutes an ingestion surface for external instructions, it is the primary purpose of the skill.
  • Ingestion points: Flow specification files and documentation located in the qa/browser-flows/ path.
  • Boundary markers: No explicit delimiters are used for the external flow content, though the skill provides a clear execution context for the agent.
  • Capability inventory: The skill can navigate to arbitrary URLs via the --base-url argument, capture screenshots, and write files to the local filesystem.
  • Sanitization: The instructions explicitly mandate that reports must be kept free of secrets, using placeholders for any sensitive values.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to interact with external web services including Gmail, Outlook, and the specified application URL. These interactions are intrinsic to its function as a QA automation tool.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill writes test results and screenshots to the qa/browser-flows/results/ directory. The instructions include a specific safeguard against credential exposure in these reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:11 PM