exploratory-test

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates as intended for a QA tool, focusing on finding bugs through structured test scenarios without any identified malicious behavior or intent.
  • [COMMAND_EXECUTION]: The skill is authorized to run CLI commands directly to facilitate testing paths and manage development servers during the testing process.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting untrusted application state (logs, screenshots, web content).
  • Ingestion points: Application logs (via Monitor tool), browser/UI output, and the local test plan file (.turbo/test-plan.md).
  • Boundary markers: No delimiters are specified to isolate application-generated text from the agent's core instructions.
  • Capability inventory: File system writes (updating test plans), CLI command execution, and browser automation.
  • Sanitization: No specific sanitization or validation of application output is implemented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:23 PM