메뉴
Export .kuzushi/findings.json as a SARIF 2.1.0 file (.kuzushi/findings.sarif) so findings are consumable by CI code-scanning, dashboards, and IDEs. Deterministic transform — no analysis. Pass "all" to include reviewed/noise findings too.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Interprocedural, hypothesis-driven hunt — finds the multi-file source→sink bugs that pattern-gating and same-file taint miss. Ranks trace anchors (entry points + dangerous sinks), then the deep-hunter agent walks each flow ACROSS files (forward/backward call-graph CLIs) over multiple rounds, confirming propagation and defeating guards, and promotes confirmed cross-file flows into findings.json with the path stored as evidenceGraph. Token-expensive, budget-bounded. Part of the HUNT phase (run via /sweep --deep, or ask for it); leads flow to /verify (panel).
Whole-file deep reader — finds bugs by READING risk-ranked files in full and reasoning from first principles, not by grepping for known patterns. Catches the long tail (project-specific wrappers, business logic, cross-function flaws) that pattern-gated producers structurally miss. Token-expensive; budget-bounded and risk-ranked. Promotes leads into .kuzushi/findings.json (source "deep-scan").
IRIS-style source→sink taint hunt. Ranks a typed CWE catalog for the repo, then drives subagents to label dangerous sinks, label sources of user input, run Joern/CodeQL dataflow queries (or same-file linking) to connect them, and triage each flow as finding/candidate/rejected. Promotes verdicts into .kuzushi/findings.json. Benefits from a prebuilt CodeQL DB / Joern CPG but degrades gracefully.
Adversarial per-threat review (Carlini doctrine). For each threat in .kuzushi/threat-model.json, state attacker capabilities, walk source→sink, attempt to bypass every guard, and assign a verdict with evidence. Promotes findings into .kuzushi/findings.json. Requires /threat-model first.
Split the attack surface into parallel-discovery partitions so fan-out hunters explore different subsystems instead of converging on the same shallow bug. Deterministic grouping of /x-ray entry points by component → .kuzushi/partitions.json, which a hunt coordinator hands to one subagent per partition. Run /x-ray first.
Empirical proof-of-concept for the PoC-ready findings. For each finding /verify marked confirmed-exploitable or inconclusive, synthesize a minimal harness that triggers the bug; a host script then runs it in a sandbox (Docker --network none when present, else a gated local run) and classifies the crash into a proof verdict. Attaches a poc block onto each finding. Requires /verify first.
| name | export-sarif |
| user-invocable | false |
| description | Export .kuzushi/findings.json as a SARIF 2.1.0 file (.kuzushi/findings.sarif) so findings are consumable by CI code-scanning, dashboards, and IDEs. Deterministic transform — no analysis. Pass "all" to include reviewed/noise findings too. |
| argument-hint | [all] |
| allowed-tools | Bash |
Convert the shared findings index into SARIF 2.1.0 for interop with CI / IDE tooling.
Run, using the project working directory as <cwd> (add --all only if $ARGUMENTS is all):
node "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/export-sarif.mjs" --target "<cwd>"
It writes .kuzushi/findings.sarif and prints { sarifPath, resultCount, ruleCount }. By
default only actionable findings are exported (status open/confirmed/proven, or verdict
exploitable/finding); pass all to include reviewed/noise too. Relay the result and the path.
Severity maps to SARIF level (critical/high → error, medium → warning, else → note); each
distinct CWE becomes a SARIF rule; the kuzushi fingerprint is carried as a partial fingerprint.
/threat-hunt, /taint-analysis, /systems-hunt)
first.