scenario-test-authoring

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill references a local PowerShell script .\scripts\validate-skills.ps1 in references/scenario-test-authoring-checklist.md for validating skill routing and document consistency. This is a standard local development task and does not involve remote code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user prompts to generate test scenarios. This is addressed by internal safety guidelines.
  • Ingestion points: User prompts intended for test scenario generation (SKILL.md).
  • Boundary markers: The 'Safety Rules' section in SKILL.md explicitly instructs to avoid private data and live-system requirements.
  • Capability inventory: Capabilities are limited to creating files under tests/scenarios/ and running local validation scripts.
  • Sanitization: Safety instructions mandate the exclusion of credentials and production data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 03:22 PM