kuzushi-security-plugin

Authorization-model review. For each endpoint / object-access candidate, determine whether an authorization + ownership check actually protects the action — find missing authz (CWE-862), IDOR / broken object-level authz (CWE-639), privilege escalation, and broken ownership. Assign finding / candidate / rejected with file:line evidence. Read-only — promotes verdicts into .kuzushi/findings.json (source 'authz').

Read-only static triage of compiled binaries (ELF / PE / Mach-O). For each detected binary and its read-only signals (dangerous imported symbols, writable+executable segments, hardening gaps from nm/readelf/objdump), judge whether the signal is a real exposure in context and tie it to source. Assign finding / candidate / rejected with the binary path as evidence. Assessment only — no execution, no exploit-oriented disassembly. Promotes into .kuzushi/findings.json (source 'binary-recon').

Proactive attack-path engine. SEARCHES for ordered entry→…→asset paths where each step is enabled by a finding — composing even sub-threshold (candidate/lead) primitives into a critical chain — using the threat-model assets, the attacker-reachable entry points, and the reachability graph. Also composes already-confirmed findings (precondition → pivot → impact). Does NOT invent findings or change their status; it overlays chains on the findings index.

Deep system-understanding pass BEFORE vulnerability work. Reads the codebase line-by-line where it matters and builds a grounded model — modules, entry points, actors, trust boundaries, data stores, and system invariants — with file:line evidence. Context only: it never finds vulns, proposes fixes, or assigns severity. Writes .kuzushi/deep-context.json.

Crypto-misuse review: non-constant-time comparison of secrets (timing side-channels), missing or compiler-elidable zeroization of secrets, and non-cryptographic RNG used to mint secrets. For each candidate, confirm the value is secret-derived, assess the leak/weakness, and assign finding / candidate / rejected with file:line evidence. Read-only — promotes verdicts into .kuzushi/findings.json (source 'crypto-review').

Measure recall / precision / false-proof rate of the pipeline against a ground-truth manifest. Scores either the bundled planted-vulnerability corpus (regression) or a live run's findings.json against a manifest you supply. Deterministic — no agent, no network. Use to prove a change to the producers helps rather than hurts.

Read-only static triage of compiled binaries (ELF / PE / Mach-O). Detects them by magic bytes, then surfaces dangerous imported symbols, writable+executable segments, and hardening gaps via on-PATH binutils (nm / readelf / objdump). Assessment only — no execution, no exploit-oriented disassembly. Promotes verdicts into .kuzushi/findings.json (source "binary-recon").

Build the heavy semantic indexes the codeql/joern backends query — a CodeQL database (per detected language) and a Joern CPG — under .kuzushi/. Runs asynchronously in the background (doesn't block the session); installs the CLI first if missing. Pass "codeql" or "joern" to build just one.

Proactive attack-path engine. The chain-finder agent SEARCHES for ordered entry→…→asset attack paths where each step is enabled by a finding — composing even sub-threshold (candidate/lead) primitives into a critical chain — using the threat-model assets, attacker-reachable entry points, and the reachability graph. Records each path (ordered narrative + member fingerprints) in .kuzushi/chains.json and attaches a `chains` ref onto each member (status unchanged). Needs ≥2 live findings.

Build a cached code-graph (.kuzushi/code-graph.json) — entry points + per-symbol caller counts (blast-radius / attack-surface signal) — so producers like /diff-review query it instead of re-deriving caller info live. Uses real Joern call edges when a CPG is built, else a deterministic ripgrep heuristic (no heavy tooling required). Re-run after large code changes.

3 hooks across 2 events

${CLAUDE_PLUGIN_ROOT}/bin/gopls

${CLAUDE_PLUGIN_ROOT}/bin/jdtls

${CLAUDE_PLUGIN_ROOT}/node_modules/.bin/typescript-language-server

${CLAUDE_PLUGIN_ROOT}/node_modules/.bin/pyright-langserver

${CLAUDE_PLUGIN_ROOT}/bin/rust-analyzer