qa-environment-checker

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local configuration files and external service health endpoints to generate readiness reports, creating a surface where malicious instructions in these sources could potentially influence the agent.\n
  • Ingestion points: Processes configuration files like package.json, .env, and playwright.config.ts, as well as service responses from URLs defined in health check patterns.\n
  • Boundary markers: The skill does not define explicit delimiters for ingested data but follows a structured report template.\n
  • Capability inventory: The skill executes shell commands for health checks, port verification, and tool availability checks as detailed in the reference files.\n
  • Sanitization: The skill follows safe practices by explicitly instructing the agent to mask secrets and environment variables in its reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:39 PM
Security Audit — agent-trust-hub — qa-environment-checker