Anthropic, OpenAI, Cloudflare and Google have each released an AI agent designed to hunt security bugs in source code. The core approach for all four tools is identical: one agent finds a bug, a separate agent attempts to disprove it, and only the survivors get patched.
The differences lie in where they run, who can access them, and how much proof they require before reporting a finding.
Why four labs shipped the same pattern in 2026
The problem every team is solving is noise. Google’s security team notes that sloppy AI code scanning produces hallucinated bugs and true-positive rates under 7%. A scanner that is wrong 93% of the time costs reviewers more than it saves.
The shared fix is separation of duties. The agent that reports a finding never gets to confirm it. Cloudflare states the rule directly in its README: the verifier is never the agent that found the bug. Anthropic, OpenAI and Google each describe a similar validation step before anything reaches a report.
The second driver is offense. The Anthropic team stated it built its scanner partly because attackers were already using AI models to find exploitable flaws. Google’s Mantis post opens by noting that models can now discover and exploit bugs with little human help.
1. Claude Security by Anthropic
What it is: A multi-agent vulnerability scanner that runs inside a Claude Code session. It is the local version of Anthropic’s hosted Claude Security product, per the plugin README.
How it works: Agents map the architecture, build a threat model, hunt across every component and verify each finding independently. The plugin offers three jobs from one menu: scan the codebase, scan changes, or suggest patches.
Output: A Markdown report along with a SARIF 2.1.0 file for GitHub code scanning. Each finding carries severity, a CWE category, impact and reproduction steps. Patches are drafted in a scratch copy and land as F<n>.patch files. The plugin never commits, pushes or opens a pull request on its own.
Cost and access: It makes no model calls of its own, so there is no separate API key. Scans count against your Claude plan’s usage limits.
Timeline: Anthropic opened a limited preview called Claude Code Security in February 2026. The hosted product reached public beta for Enterprise customers on Claude Opus 4.7. The Claude Code plugin entered beta on July 22, 2026. In August, the hosted scanner moved to Claude Mythos 5.
Where it fits: Anthropic positions it as one layer. The security-guidance plugin checks code as Claude writes it, and /security-review does a single pass on a branch. Claude Security is the on-demand deep scan.
2. Codex Security by OpenAI
What it is: A CLI and TypeScript SDK, published as @openai/codex-security, for finding, validating and fixing vulnerabilities.
How it works: It scans a whole repo, selected paths, or a Git diff. A –mode deep flag runs parallel discovery workers. It validates candidate findings, generates patches and can verify existing fixes. A cs policy command drafts a SECURITY.md that tells future scans what counts as a vulnerability in your project.
Output: Threat models, SARIF, JSON or CSV exports, plus publishing to Linear. It can import GitHub code-scanning alerts and suggest owners from Git history. A GitHub Action runs scheduled or pull-request scans; findings are report-only by default.
Cost and access: The client is Apache-2.0, but the scanner behind it is not. DevOps.com notes the CLI and SDK stay in limited beta for approved customers. The README lists OpenAI, Amazon Bedrock, OpenRouter and Fireworks AI as providers. Requires Node.js 22.13+ and Python 3.10+.
3. Security Audit Skill by Cloudflare
What it is: An MIT-licensed skill that turns any capable coding agent into a security auditor.
How it works: A 6-phase audit.
- Reconnaissance: map architecture, trust boundaries and input surfaces into architecture.md and a coverage ledger.
- Coverage-led hunting: isolated hunters each take ledger units; coverage critics look for gaps.
- Candidate validation: a fresh verifier tries to disprove every unique candidate.
- Structured output: confirmed, needs_validation and rejected records go to findings.json, checked against a schema.
- Independent record verification: new agents re-verify every final source claim.
- Target-neutral reporting: REPORT.md and detail files are derived from the verified records.
Requirements: A coding agent that supports tool use and parallel sub-agents, plus Node.js for the validators. It also wants an OS-enforced sandbox with no external network. Without one, leads stay needs_validation instead of being executed.
Then ask the agent: “security audit this codebase.” Output defaults to ~/security-audit-skill/<repo-name>/run-<N>, outside your repo.
The data behind it: Cloudflare published the skill on June 18, 2026, with its post Build your own vulnerability harness. The roughly 450-line skill seeded an internal harness that now scans 128 repos. Cloudflare reports these lifetime numbers:
- 20,799 raw candidates from discovery, about 12,057 of which survived validation.
- 13,841 findings in the shared triage pool across 145 repos, including another harness’s output.
- 5,442 folded away as duplicates and 1,154 routed out as wrong-repo or low-risk.
- 7,245 actionable findings sent to engineering teams.
Better recon context cut the first-pass rejection rate from 40% to 11%. Cloudflare also uses one model for discovery and a different model for triage, so models check each other.
4. Mantis by Google
What it is: An Apache-2.0 set of security-review skills plus an ADK reference harness for AI coding agents. Google team states that it is part of how it finds and fixes bugs internally.
How it works: Mantis reads the repo’s history to learn from past security fixes. It builds a hierarchical summary tree, condensing files into directory and root summaries. Google team states that this cut token overhead by over 85%. It then generates a threat model and hypotheses, hunts, deduplicates and critiques findings.
What sets it apart: Reproduction and patch verification. Mantis tries to reproduce each bug, from a static exploit sketch up to a unit test or mock server. It patches with an adversarial loop that attacks the fix. It also calibrates severity against a rubric to stop “thousands of criticals.” A mantis-advise skill then feeds what it learned back into code generation.
Setup: Clone the repo and point any coding agent at it, or run the ADK harness directly. The harness supports a –focus prompt such as “look for IDOR” and a –max-tokens spend ceiling.
What it means
Developers using these tools do not see a change in customer-facing products, API behaviour or privacy policies. These are research infrastructure tools. They do not imply changes to internal model training or evaluation unless explicitly stated by the vendor.
