The closed loop Hunt → Fix → Verify plus its two automation runtimes. Expand any box to see its phases/stages and the files that implement them. Works without JavaScript.
/vulnhunt — the scanner (prompt-only skill)An orchestrator that never analyses code itself — it dispatches a subagent per phase and verifies each output file. Attacker-first: start at every user-controllable input, trace forward to dangerous sinks, then try to disprove each candidate. Never edits the target; fixes are documented, not applied.
*_VULNHUNT_RESULTS_* dir with report README.md, PoCs, exploit tests.Enumerate every attacker-controllable entry point (HTTP handlers, CLI, queue consumers, gRPC, file uploads), partition the codebase into subgraphs, and mark production vs test/dev reachability.
phase1_output.md — input inventory + partition table.phases/phase1_recon.md
For each production partition, spawn one agent per vulnerability class — INJ (injection), NAV (navigation & access control), LOG (logic & crypto) — plus one sink-driven audit agent. Each traces inputs forward to sinks. Minimum agents = (3 × partitions) + 1.
results/.A pass that actively tries to disprove each candidate — flawed assumptions, missing preconditions, mitigating controls. Roughly half of candidates are eliminated here. This is what keeps false positives low.
phase2b_output.md — confirmed findings only.phases/phase2b_verify.md
For each surviving finding: write a PoC, an executable exploit test, and a fix strategy (description, not an applied edit). Read-only mode writes static PoCs; bash-enabled mode runs them.
poc/, exploit_tests/, phase3_output.md (VULN-NNN table).Grep each confirmed root-cause pattern across the whole codebase so a single fix covers all instances, not just the one that was traced.
phase3d_output.md — sweep table + per-instance triage.phases/phase3d_sweep.md
The orchestrator assembles the input inventory with dispositions, one VULN-NNN per sink location, PoCs, fix strategies, the sweep table, and a separate Code Quality (code smells) section. Zero findings is a valid outcome.
phases/phase4_report.md → results dir README.md
/vulnhunter-fix — the fixer (prompt + Python helpers)Developer-led, test-driven remediation. Unattended within a phase, but pauses at every phase boundary for an operator Approve/Pause. Never edits a source file until RED evidence exists on disk.
vulnhunter-labelled GitHub issues (in-place) or a results dir (fork mode) → Out: a reviewable PR with exploit + test + fix.Pull findings from issues or the results dir and cluster related ones so one PR fixes a whole root cause.
prompts/parse.md · prompts/parse_issues.md · scripts/issue_intake.py · scripts/cluster_score.py
Route each cluster to a model tier by severity/CWE (see config.json → models.routing) and pick the remediation approach.
prompts/plan.md · prompts/plan_fork.md · prompts/tier_judgment.md · scripts/parse-tier-judgment.py
Exploit demo → failing security test (RED) → implement fix (GREEN) → confirm exploit blocked → regression check → commit. Worker agents are CWE-family specialised.
prompts/implement.md · prompts/agent_fix.md · prompts/worker_agent_{authz,crypto,injection,config,resource,common}.md
Independent reviewer test pass per cluster; schema-validated results with a repair loop.
prompts/verify.md · prompts/reviewer_test.md · scripts/validate-*.py
gh pr createSeverity-mask, body-completeness, scope, idempotency, anti-merge, and verification-table gates all run before any PR opens.
prompts/deliver.md · scripts/run-gates.py · scripts/check-*.py · templates/pr_body*.md · vulnhunter_fix/delivery.py
Wraps Graphify AST extraction (dist graphifyy) into the fixer's own schema, with a content-hash cache and a grep fallback when AST extraction can't run.
vulnhunter_fix/graph/{build,query,schema,config,fallback}.py · scripts/build_graph.py
/vulnhunt-fix-verify — independent verifier (prompt-only)A separate, strictly read-only agent — Read/Write/Edit/Glob/Grep/Agent, no Bash, no network. The developer's word is a claim, not evidence; only the code is evidence. The caller must pre-create the out directory.
repo= report= fixed=VULN-… out= → Out: per-finding verdict JSON.Reject missing/non-absolute args; establish the trusted roots (repo + additional_repos).
phases/phase0_preflight.md → out/phase0_state.json
Read the prior report and extract only the fixed= findings.
phases/phase1_extract.md → out/extracted_findings.md
Statically confirm whether each finding is actually remediated in the supplied code.
phases/phase2_verify.md → out/disposition_VULN-NNN.json (one per id)
Combine dispositions into the final artifact. (Phase 3 is intentionally reserved for future exploit-test replay.)
phases/phase4_emit.md → out/verify_disposition.json
vulnhunter-agent/ — headless runtimeRuns /vulnhunt unattended via the Claude Agent SDK: clone → scan → publish → file GitHub issues; also a --mode=verify path. All hosts/credentials/paths come from TOML + VULNHUNT_* env — nothing sensitive is hardcoded.
Three interchangeable token managers behind one get_valid_token(): api_key (default), bedrock_oauth, bedrock_sigv4.
agent/auth.py · agent/token_client.py · agent/build_settings.py · agent/config.py
Drives the SDK, streams events, retries on 429, then writes a schema-validated manifest — the stable integration contract.
agent/runner.py · agent/_stream_events.py · agent/manifest.py · scan_manifest.schema.json
Optionally push results to a separate repo and post one deduplicated GitHub issue per confirmed finding (or a clean-scan receipt).
agent/publish.py · agent/issues*.py (fetch/extract/dedup/render/remote_report)
Orchestrates /vulnhunt-fix-verify and posts verdicts; optional JSONL lifecycle audit.
agent/verify*.py · agent/audit.py · verify_disposition.schema.json
harness/ — batch & benchmark (dev-only)Workstation-scale tooling that shells out to claude -p /vulnhunt …. Not part of the shipped product.
Clone + scan every repo in REPO_LIST.txt, resumable, with status/collect commands.
local_harness/batch/run.py · local_harness/scan.py · local_harness/clone.py
Clone → scan → LLM-judge against a known-vulnerable corpus → tally metrics. Bring your own ground_truth/<repo>.json.
local_harness/benchmark/{run,judge,tally,analyze_misses,finding_history}.py
Generated for new-joiner onboarding · counts from CodeGraph & Graphify (see tool-outputs/). Source: github.com/capitalone/VulnHunter (Apache-2.0).