Captures redacted, provenance-aware cybersecurity observations with shared status fields, independent ground truth, and honest limitations. Use when recording exercise evidence, findings, validation results, or security-review handoffs.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Record what was observed, how it was sourced, and what remains unknown; never turn absence of proof into proof.
cyber-evidence/
├── SKILL.md
├── references/evidence-record.md
└── evals/evals.jsonengagement_scope_ref, skill_version, and source.observed_at, observer, method, and evidence references; redact secrets and sensitive payloads.lab_validation extension with transitive binding chain: ObservationRecord.action_receipt_ref -> ActionReceipt.gate_ref -> GateDecision.request_ref -> ActionRequest. Unpaired analysis uses the base record directly.finding_status: confirmed, suspected, blocked, not-tested, or false-positive. Retain prior corroborated findings if a retest step blocks.blocked, prevented, detected, responded, or telemetry-gap.artifacts/security-review.md when a continuous workflow chain owns it.
Base fields: engagement_scope_ref, skill_version, source, observed_at, finding_status, evidence_refs, limitations, accountable_owner. Optional metadata: observer, method, expected_observation, authorization_ref, redaction_note, independent_ground_truth_ref.finding_status: not-tested only when no supplied or exercised evidence exists (AC-CLV-11); blocked finding denotes an evidence-backed barrier, not a mechanical step-state copy.false-positive without independent invalidating evidence.telemetry-gap (AC-CLV-12). An observation alone cannot prove an action occurred.residual or unverified state (AC-CLV-13); post-expiry teardown requires surviving authority.(run_id, attempt_id, test_id) is immutable per attempt; conflicting or reused keys are rejected.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.