Radar / AI security / Detectify Agentic Tooling
Detectify Agentic Tooling: prove what your AI security agent actually tested
Detectify's new tooling lets an organization's own AI agents investigate suspected vulnerabilities against live applications, with an append-only Security Ledger recording the evidence behind every verdict.
Why it matters
It answers the trust problem in AI security testing: the ledger is written by Detectify's tools, not the agent, so a finding backed by real tests cannot be faked by a confident model.
What you could build with it
A DevSecOps team drowning in AI-generated SAST findings could route every suspected vulnerability through Detectify's tooling for a month, then compare the ledger-backed confirmed rate against the raw AI report rate and report how much triage time the evidence trail actually saves.
Does it hold up?
Too early to judge: available on request from 16 November, with no public deployments or independent reviews yet; the ledger concept is only proven once teams audit real agent verdicts against it.
Built with Detectify Agentic Tooling
- Detectify's Agentic Tooling lets AI agents test suspected flaws in running applicationsarticle · SiliconANGLE on the launch, the Security Ledger's append-only evidence record, and the pitch to DevSecOps teams unsure whether to trust agent findings.
- Detectify launches Agentic Tooling to verify AI security findingsarticle · SC Media brief on the MCP/CLI integration, the 80%-noise figure for AI SAST findings, and the ledger's role in separating verified threats from unsupported conclusions.
- Detectify's Agentic Tooling Tests Suspected Flaws in Running Appsarticle · Coverage of the per-ticket verification loop, the add-only ledger, and the fact that Detectify never accesses or stores customer codebases.
Learn more
First spotted on article: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.