Help us improve
Share bugs, ideas, or general feedback.
Link related findings into higher-impact attack chains. The chain-finder agent reasons over the findings index for compositions (precondition → pivot → impact) — e.g. an auth bypass that turns a read-only SSRF into internal RCE — and records each chain with an ordered narrative + member fingerprints in .kuzushi/chains.json, attaching a `chains` ref onto each member finding (status unchanged). Needs ≥2 live findings.
npx claudepluginhub allsmog/kuzushi-security-plugin --plugin kuzushi-security-pluginHow this skill is triggered — by the user, by Claude, or both
Slash command
/kuzushi-security-plugin:chainchain-finderThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Findings are triaged independently; this connects them into **attack chains** where one finding
Searches USPTO patent and trademark records from official APIs including PatentSearch, TSDR, and assignment databases.
Share bugs, ideas, or general feedback.
Findings are triaged independently; this connects them into attack chains where one finding
escalates another's impact. Requires ≥2 live findings in .kuzushi/findings.json (run the hunts
first).
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.fingerprint verbatim as a member id.
Write the { chains: [...] } bundle to the prep's draftPath. If nothing genuinely composes,
write { "chains": [] } — don't force a chain.assembleCommand (finalize). It validates each chain (≥2 real members, ordered
narrative), writes .kuzushi/chains.json, and attaches a chains ref onto each member finding
(status unchanged). Report the chains highest-escalated-impact first.