Cyclops V2

A ground-up rebuild. v1 was a code-*reader* that pattern-matched known bug shapes, drifted to low-severity IDOR/BAC/SSRF, never proved RCE, and only ever found sibling-CVEs. v2 is built on one law: only an execution artifact may declare a finding - an ASan crash, a popped shel...

Project page on zionboggan.com ↗

4 commits First commit Jul 3, 2026 Last commit Jul 6, 2026 (1 month ago)

Code Commits Tags

Markdown 45.8%Python 23.7%YAML 20.1%Shell 10.3%

Files 50 entries

▸bin/
- ◇sync.sh
▸brain/
- ▸joern-queries/
  - ◇_runner.md
  - □c-memory-corruption.sc
  - □command-injection.sc
  - □deserialization-rce.sc
  - □js-electron-rce.sc
  - □path-traversal.sc
  - ◇README.md
  - □ssrf.sc
  - □template-injection.sc
- ▸semgrep-rules/
  - ◇command-injection.yaml
  - ◇deserialization.yaml
  - ◇electron.yaml
  - ◇ml-unsafe-load.yaml
  - ◇path-traversal.yaml
  - ◇ssrf.yaml
  - ◇template-injection.yaml
- ◇brain.py
▸findings/
- ◇F001-gguf-tools-oob-read.md
▸memory/
- ◇memory.py
- ◇selftest.py
▸oracle/
- ◇crash_demo.py
- ◇oracle.py
- ◇triage_new_crashes.sh
▸orchestrator/
- ◇e2e_proof.sh
- ◇feed.py
- ◇orchestrator.py
- ◇seed_graph.py
▸targets/
- ◇deep_campaign.sh
- ◇deep_loop.sh
- ◇hunt_gguf.sh
- ◇hunt_llamacpp.sh
- ◇patch_gguf_fuzzdepth.py
▸vault/
- ▸.obsidian/
  - ◇app.json
- ▸00-doctrine/
  - ◇OPERATING-CORE.md
  - ◇SEVERITY-GATE.md
- ▸01-archetypes/
  - ◇ai-agent-mcp.md
  - ◇cicd-supplychain.md
  - ◇devops-infra.md
  - ◇electron-desktop.md
  - ◇memory-unsafe-parsers.md
  - ◇ml-model-loaders.md
- ▸04-cleared-axes/
  - ◇README.md
- ▸06-methods/
  - ◇NOVELTY-DOCTRINE.md
- ◇README.md
◇.env.example
◇.gitignore
◇README.md
◇requirements.txt
◇VALIDATION.md

README.md

Cyclops v2 - execution-grounded vulnerability research

A ground-up rebuild. v1 was a code-reader that pattern-matched known bug shapes, drifted to low-severity IDOR/BAC/SSRF, never proved RCE, and only ever found sibling-CVEs. v2 is built on one law: only an execution artifact may declare a finding - an ASan crash, a popped shell, a retrieved secret. Never an LLM's opinion.

The three pillars

Pillar	What	Where	Fixes
1 - Memory	KuzuDB graph (targets→hypotheses→proofs→findings + cleared-axes) + Chroma (semantic recall) + Redis (queue/cache) + Obsidian `vault/`	`memory/`, `vault/`	drift, tunnel-vision, re-screening
2 - Brain	Semgrep fast-pass → Joern CPG dataflow (reachable source→sink) → CodeQL deep	`brain/`	sibling-CVE-only; finds novel unexplored sinks
3 - Oracle	libFuzzer/AFL++ + ASan/UBSan → crash triage (GEF) → Docker/CT detonation	`oracle/`	never proved RCE; the only thing that creates a finding

The severity gate (vault/00-doctrine/SEVERITY-GATE.md) is a refusal engine: 8 P1 impact families, each with its exact oracle and its v1 overclaim traps ("injection reachable" ≠ "ATO completes"; "read DoS" ≠ "RCE"). Anything below the gate goes to the cleared-axes log, never to a finding. Enforced in code: memory.promote_to_finding() raises unless a non-DISPROVEN Proof exists.

Where it runs

Everything runs on the forge box (CT 236, REDACTED-IP) - it holds the heavy tools (Joern, CodeQL, AFL++, clang/ASan, Ghidra, KLEE, SymCC) and the venv (/opt/cyclops-venv). Redis + KuzuDB are forge-local (Redis bound to localhost - never LAN, that's a gate family). The repo + human-readable vault/ live on CT 215 (/shared/projects/cyclops-v2, Samba-readable so Zion opens the vault in Obsidian). Sync: rsync -az cyclops-v2/ root@REDACTED-IP:/opt/cyclops-v2/.

Operate

# on forge (CYCLOPS_HOME=/opt/cyclops-v2, PY=/opt/cyclops-venv/bin/python)
$PY orchestrator/seed_graph.py            # seed archetypes + sink classes + gate
$PY orchestrator/feed.py 21               # poll fresh releases (<=21d) -> targets queue
$PY orchestrator/orchestrator.py drain-targets   # brain pass on each fresh target
$PY orchestrator/orchestrator.py drain-oracle     # route hypotheses to proof
$PY orchestrator/orchestrator.py status   # graph + queues + GATED findings

Configuration is via environment variables, each with an in-code default: copy .env.example to .env and set only the values that differ from your box.

The loop: feed → brain (hypotheses) → oracle (proof) → gate (finding) → vault. Novelty by construction: hunt days-old code (feed.py), CPG finds unexplored source→sink paths, sibling-CVE gate runs before deep work.

Validated

orchestrator/e2e_proof.sh runs the whole chain on real cJSON source (brain CPG → oracle fuzz → ASan crash → triage → gated finding). memory/selftest.py proves the gate refuses findings without proof and honors DISPROVEN (9/9 pass).

Tooling reality (honest)

Present + verified: Joern (CPG dataflow proven), CodeQL 2.25.1, Semgrep 1.166, AFL++ 4.0, clang-14 + libFuzzer/ASan/UBSan (compile proven), GEF, Ghidra, KLEE, SymCC, Docker 29, KuzuDB 0.11, Chroma 1.5, Redis 8.
rr unavailable: this is an unprivileged LXC (perf_event_paranoid=4, no HW perf counters). Crash→exploit triage uses GEF + the ASan report instead.
Firecracker/microVM unavailable: no /dev/kvm in the LXC. Detonation uses Docker on forge + the isolated detonation CT (302) for risky targets.