Ross ROSS = Recommend OSS · open-source software intelligence for agents

Lazarus-AI/clearwing

None observed · 2026-09-03

github.com/Lazarus-AI/clearwing · Python · MIT (permissive) observed · 2026-09-03

Health v2 · maintenance only

63/100

  • Activity 100
  • Release rhythm 47
  • Longevity 10

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 141
  • days_rel: 141
  • days_push: 0
  • n_releases_24m: 1

Full methodology

Adoption not part of the score

1063 stars · 159 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Clearwing is a dual-mode autonomous offensive-security tool that combines a network-pentest ReAct agent with an LLM-driven source-code vulnerability hunter. It validates findings with sanitizer crashes and PoC reproduction, generates SARIF/markdown reports, and supports N-day exploit development, binary reverse engineering, and responsible disclosure workflows.

Use cases

  • find vulnerabilities in source code automatically
  • run an AI pentest agent against my network
  • develop exploits for known CVEs
  • scan repositories for memory-safety bugs with ASan verification
  • decompile a binary and hunt for bugs with Ghidra and an LLM
  • generate SARIF vulnerability reports for disclosure
  • benchmark LLMs on vulnerability-finding ability

When to choose

  • you need autonomous, evidence-graded vulnerability discovery with crash-verified findings
  • you want an agentic pentest tool with human-approval guardrails on exploitation
  • you run security campaigns across many repositories with budget and checkpointing
  • you need N-day exploit development or binary-to-source vulnerability hunting

When to avoid

  • you lack explicit authorization to test the target - it is a dual-use offensive tool
  • you need a passive SAST scanner without LLM costs or agent loops
  • you require a Windows-native or GUI-first security workflow
  • you want a fully automated exploit tool with no human-in-the-loop gates

Facets

cli-tool · maturity active

penetration-testing vulnerability-scanning agent-framework llm-inference reverse-engineering security benchmarking testing security penetration-testing artificial-intelligence developer-tools reverse-engineering python cli offensive-security vulnerability-discovery exploit-development sarif-reports responsible-disclosure cve-exploitation fuzzing-verification human-in-the-loop ai-agents linux docker

1 source

Member repositories

RepositoryRoleHealth v2
Lazarus-AI/clearwingmain63

For agents

markdown · JSON · MCP: product_card(name="Lazarus-AI/clearwing")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem