メニュー
Report and query evidence-backed security findings from authorized CyberEdge Tasks. Use for versioned scanner adapters that classify existing Observations, never for arbitrary command or PoC execution.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/Symph0nia/CyberEdge --skill cyberedge-report-findingsコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Run or continuously monitor one evidence-backed CyberEdge assessment workflow for an explicitly authorized Scope. Use when an AI operator must check readiness, expand domain assets, inventory services and websites, run bounded vulnerability and intelligence stages, follow one Task, create an explicitly requested recurring assessment, inspect exposure changes, and report exact coverage without claiming unavailable adapters were completed.
Correlate exact, evidence-backed CPE identities already observed by CyberEdge with normalized NVD CVE records. Use when an AI operator must run CVE intelligence for an authorized Scope, interpret CVSS metadata and lifecycle state, or distinguish completed CPE coverage from missing identity or provider failure without guessing products or versions.
Search bounded GitHub public-code metadata for exact domain names in an explicitly authorized CyberEdge Scope. Use when an AI operator must run public-code intelligence, inspect evidence-backed reference candidates, or distinguish completed negative coverage from provider failure without retrieving source content or claiming confirmed credential leakage.
SOC 職業分類に基づく
SKILL.md を表示中
| name | cyberedge-report-findings |
| description | Report and query evidence-backed security findings from authorized CyberEdge Tasks. Use for versioned scanner adapters that classify existing Observations, never for arbitrary command or PoC execution. |
Use cyberedge-agent. This bridge is machine-only.
1=INFO, 2=LOW, 3=MEDIUM, 4=HIGH, or 5=CRITICAL.The server deduplicates by Scope, detector, rule, Asset, and fingerprint. A repeated observation refreshes the existing Finding instead of creating noise.
{"request_id":"req-1","idempotency_key":"idem-1","agent_id":"codex-main","skill_name":"cyberedge-report-findings","skill_version":"0.1.0","action":"report_finding","task_id":"task-id","observation_id":"observation-id","detector":"adapter-name","rule_id":"rule-id","title":"Finding title","description":"Evidence-backed description","severity":3,"fingerprint":"stable-fingerprint"}
Use search_findings with scope_id for the resulting read model and get_task_report for the complete Evidence chain.