Validates defensive controls with paired authorized action and observation evidence, distinguishing blocked, prevented, detected, responded, and telemetry-gap outcomes. Use for purple-team validation design or offline fixture review; not unsanctioned testing or production efficacy claims.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
No defensive outcome without linked action and observation evidence.
Input: control hypothesis, permitted action, scope/approval, mode (analysis, replay, isolated-lab-validation, defensive-verification), entity, window, expected observation, stop condition.
Process: classify active effects (active: true for any interaction outside supplied-artifact reasoning; reading supplied events/files is non-active analysis); verify fresh host gate before active actions; capture ActionReceipt and ObservationRecord; enforce transitive binding chain: ObservationRecord.action_receipt_ref -> ActionReceipt.gate_ref -> GateDecision.request_ref -> ActionRequest.
Output: purple outcome enum, finding status, evidence references, limitations, stage fidelity, owner.
analysis, replay, isolated-lab-validation, or defensive-verification.(run_id, attempt_id, test_id).observation_id and transitive binding chain.blocked, prevented, detected, responded, or telemetry-gap.verified-clean, residual, unverified, not-applicable).telemetry-gap (AC-CLV-12). An observation alone cannot prove an action occurred.blocked: denied or could not run; prevented: control stopped action; detected: observation identified behavior; responded: independently evidenced approved response; telemetry-gap: action exists without observation.residual or unverified with accountable owner (AC-CLV-13).HoangNguyen0403/agent-skills-standard
11c8bd1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.