Skill v1.0.0
currentLLM-judged scan95/100version: "1.0.0" name: skill description: > Deep routing entry for the Clown 2.1 authorized security workflow. It coordinates collection, target profiling, specialist validation, evidence quality, and replay without opening unrelated branches.
Clown 2.1 Deep Entry
Read this file after the package root entry when the task needs detailed routing. The canonical workflow is:
scope -> profile -> collect -> normalize -> prioritize-> hypothesis -> validate -> evidence -> report -> replay
Route Table
| Need | Primary lane | |
|---|---|---|
| Search, HTML, JavaScript, browser, or response extraction | skills/specialized/snoweyes-collector/SKILL.md | |
| Asset graph, technology, role, tenant, and trust boundary | skills/specialized/target-profiling/SKILL.md | |
| Iterative authorized discovery and seed management | skills/specialized/src-hunt-lane/SKILL.md | |
| API, token, object, schema, transport, or file boundary | skills/specialized/api-security/SKILL.md | |
| Payment, order, quota, workflow, approval, or state integrity | skills/specialized/business-logic-attack/SKILL.md | |
| Reproduction, impact, severity, and submission readiness | skills/specialized/src-report-paradigm/SKILL.md |
Canonical Knowledge Base
The detailed checks live in knowledge-base/. Start with knowledge-base/README.md, then open the smallest file matching the current signal:
recon-methodology.mdfor asset and route modeling;idor-test.mdfor object and function authorization;authbypass-test.mdandoauth-jwt-test.mdfor identity and token
boundaries;
api-gateway-test.md,graphql-test.md, andwebsocket-test.mdfor API
transport and schema boundaries;
logic-test.mdandrace-condition-test.mdfor business-state integrity;injection-test.md,ssrf-test.md,xss-test.md, and
file-upload-test.md for input and content boundaries;
info-leak-test.md,path-traversal-lfi-test.md, and
http-smuggling-test.md for exposure and request-boundary signals.
Evidence Contract
Every lane must preserve:
scope_ref:run_id:asset:source:observed_at:hypothesis:baseline:mutation:response_delta:state_effect:impact:cleanup:evidence:status:next_action:
The status is one of confirmed, incomplete, negative, or blocked. Missing proof is recorded as a gap; it is never filled by inference.
Operating Rules
- Use passive collection first.
- Keep one active hypothesis per branch.
- Change one variable per validation.
- Preserve provenance and redact secrets.
- Stop on scope ambiguity, rate limiting, unexpected state change, or
unbounded impact.
- Load one expert module only when a primary lane identifies a concrete need.
- Return all expert results to the same evidence contract.
The architecture contract is in references/architecture/route-contract.md. The machine-readable registry is in references/architecture/skill-registry.json.