{"id":19606,"plugin_id":"plugins_6a9a4a13b2088191832975a573c4b649","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:40.837Z","digest":"780989822659bd362b7ea49869142ea16dbee839355df9b251e23f163362f73e","against":null,"payload":{"name":"copilot-evaluation-red-team","description":"Evaluates Copilot scenarios against safety, privacy, and red-team gates.","included_files":[],"skill_md_contents":"---\nname: copilot-evaluation-red-team\ndescription: Evaluates Copilot scenarios against safety, privacy, and red-team gates.\n---\n\n## Architect edition scope\n\nThis edition produces local plans, checks and review artifacts only. Instructions below describing provisioning, deployment, API calls, runtime tests or publishing are plans for an authorized operator, not actions to execute. Never connect to or modify an environment through this edition. No runtime test or deployment may be claimed from generated checklists.\n\n# Copilot Evaluation & Red Teaming\n\nUse `copilot-guardrails.md`. Test prompt injection, data exfiltration, incorrect grounding sources, and unsafe actions. Autonomous writes remain blocked without an approved execution manifest.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}