Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

chain

Estrellas0

Forks0

Actualizado29 de mayo de 2026 a las 02:51

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.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

allsmog

allsmog/kuzushi-security-plugin

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Analistas de seguridad de la informaciónOcupaciones informáticas y matemáticas·SOC 15-1212

SKILL.md

readonly

name	chain
description	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.
context	fork
agent	chain-finder
user-invocable	false

Attack-path chaining

Findings are triaged independently; the highest-impact issues are often a path assembled from individually-unremarkable bugs (a low info-leak + a medium auth gap + a candidate SSRF ⇒ critical RCE). This searches for those paths — it doesn't just restate confirmed findings. Requires ≥2 live findings in .kuzushi/findings.json (run the hunts first); richer with a threat model + code-graph built (they supply the assets + reachability the search keys off).

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/chain-prepare.mjs" --target "<repo root>". If there are fewer than 2 live findings, tell the user to run more hunts and stop. Read prepPath — it carries the findings (incl. sub-threshold leads), the crown-jewel context.assets, the attacker-reachable context.entryPoints, and a context.reachability summary.
Search entry→asset paths (forward from entry points, backward from assets, meet in the middle) where each step is enabled by a finding; compose sub-threshold primitives where the composition is what makes it critical. Order members, name the data/control link between steps, and use each fingerprint verbatim. Write { chains: [...] } (with kind/entryPoint/asset) to draftPath. If nothing genuinely composes, write { "chains": [] } — don't force a chain.
Run the assembleCommand (finalize). It validates each chain (≥2 real members, ordered narrative ≥120 chars), escalates severity to at least the max member's (composed impact is never under-reported), writes .kuzushi/chains.json, and attaches a chains ref onto each member (status unchanged). Report the paths highest-impact first; /report renders them.

When NOT to use

Before ≥2 live findings exist — run /sweep / /threat-hunt / /taint-analysis first.
To discover new bugs — chaining only connects existing findings; name missing links as gaps.

Rationalizations to Reject

"All low/candidate — not worth chaining." → Composing sub-threshold primitives into a critical is the whole point; severity-gating the links misses the chains that matter most.
"Same bug class, so they chain." → A link needs one finding's effect to satisfy the next's precondition — name that edge or drop it. Co-occurrence ≠ composition.

Más de este repositorio

mismo repositorio

deep-hunt

allsmog/kuzushi-security-plugin

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).

2026-06-110

deep-scan

allsmog/kuzushi-security-plugin

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").

2026-06-110

taint-analysis

allsmog/kuzushi-security-plugin

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.

2026-06-110

threat-hunt

allsmog/kuzushi-security-plugin

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.

2026-06-110

partition

allsmog/kuzushi-security-plugin

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.

2026-06-100

poc

allsmog/kuzushi-security-plugin

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.

2026-06-100

name	chain
description	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.
context	fork
agent	chain-finder
user-invocable	false

Attack-path chaining

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/chain-prepare.mjs" --target "<repo root>". If there are fewer than 2 live findings, tell the user to run more hunts and stop. Read prepPath — it carries the findings (incl. sub-threshold leads), the crown-jewel context.assets, the attacker-reachable context.entryPoints, and a context.reachability summary.
Search entry→asset paths (forward from entry points, backward from assets, meet in the middle) where each step is enabled by a finding; compose sub-threshold primitives where the composition is what makes it critical. Order members, name the data/control link between steps, and use each fingerprint verbatim. Write { chains: [...] } (with kind/entryPoint/asset) to draftPath. If nothing genuinely composes, write { "chains": [] } — don't force a chain.
Run the assembleCommand (finalize). It validates each chain (≥2 real members, ordered narrative ≥120 chars), escalates severity to at least the max member's (composed impact is never under-reported), writes .kuzushi/chains.json, and attaches a chains ref onto each member (status unchanged). Report the paths highest-impact first; /report renders them.

When NOT to use

Before ≥2 live findings exist — run /sweep / /threat-hunt / /taint-analysis first.
To discover new bugs — chaining only connects existing findings; name missing links as gaps.

Rationalizations to Reject

"All low/candidate — not worth chaining." → Composing sub-threshold primitives into a critical is the whole point; severity-gating the links misses the chains that matter most.
"Same bug class, so they chain." → A link needs one finding's effect to satisfy the next's precondition — name that edge or drop it. Co-occurrence ≠ composition.