DAILY DROP · NOV 4, 2026

Today's drop: 2 new tools, 2 listing updates

The directory now lists 137 hand-checked tools. New today: AI-Infra-Guard, Tencent's free, open-source AI red teaming platform that scans AI infrastructure, MCP servers, agent skills and agents and tests models for jailbreaks, and CISO Assistant, an open-source GRC platform for risk and compliance work with an optional local AI chat. Updated: AiSOC (v22.0.0 fixes seven security advisories, so update now) and Security Onion (3.4.0 with Agentic AI Automations for Pro). AI for IT & Cybersecurity grows to 52 tools. Pricing only where the official page states it.

Previous drop: Nov 3, 2026 →

Get the weekly dropThe best new AI tools, one email a week. Free.

New in the directory 2

Browse all 137
Tool
Category
Price
Status
Link
AI-Infra-Guard (Tencent)Free, open-source (Apache-2.0) AI red teaming platform from Tencent's Zhuque Lab, also called A.I.G. Five scanners in one web UI: AI infrastructure scanning that fingerprints AI services on a domain, IP or URL and matches known vulnerabilities, MCP server scanning, agent skill auditing, agent scanning that sends test prompts to a running agent, and LLM jailbreak evaluation of any OpenAI-compatible model. Start it with Docker Compose (4 GB RAM, 10 GB disk) and open localhost:8088, or pip install each scanner on its own (aig-infra-scan, aig-mcp-scan and others). The MCP, skill and agent scans use an LLM API key you supply. It has no login, so Tencent says never to expose it on a public network. About 7,400 GitHub stars, weekly releases (v4.6.8 on Oct 29, 2026) and a Black Hat Europe 2025 Arsenal demo. Only scan systems you own or are authorized to test.
Price Free and open source (Apache-2.0); LLM usage billed by your AI provider
FREE TIERchecked 11/04
CISO AssistantOpen-source GRC (governance, risk and compliance) platform from intuitem for risk assessments, audits, vendor risk and compliance tracking against 200+ frameworks, including ISO 27001, NIST CSF, SOC 2, CIS Controls, PCI DSS, HIPAA and CMMC, with automatic mapping between frameworks so one control counts toward several. An optional AI chat mode (off by default) answers questions about your risks, controls and frameworks using a local model through Ollama, LM Studio or llama.cpp, or any OpenAI-compatible endpoint, with a Qdrant vector store. Self-host the free Community edition with Docker Compose, or start a free trial of the cloud version. About 4,600 GitHub stars; v4.2.0 shipped Nov 1, 2026.
Price Community edition free (self-hosted, AGPLv3); Pro SaaS from €39/contributor/mo billed annually; free cloud trial
FREE TIERchecked 11/04

Why these two

  • AI-Infra-Guard (A.I.G) puts five AI security scanners behind one web UI. It fingerprints AI services such as model servers and agent tools on a host and matches known vulnerabilities, scans MCP server code, audits agent skills, sends test prompts to a running agent and runs jailbreak evaluations against any OpenAI-compatible model. It comes from Tencent's Zhuque Lab, is free under Apache-2.0, has about 7,400 GitHub stars and ships a release almost every week (v4.6.8 on Oct 29 split each scanner into its own pip package). We already list single-purpose scanners like SkillSpector, Snyk Agent Scan and garak; A.I.G is the one place to run all of those checks. It has no login, so keep it on a lab network, and only scan systems you own or are allowed to test.
  • CISO Assistant is a different side of security: governance, risk and compliance. It tracks risk assessments, audits and vendor reviews against 200+ frameworks, including ISO 27001, NIST CSF, SOC 2, CIS Controls, PCI DSS and HIPAA, and maps controls between frameworks so one piece of evidence counts toward several. An optional AI chat mode (off by default) answers questions about your own risks and controls using a local model through Ollama or LM Studio. The Community edition is free to self-host under AGPLv3; Pro SaaS starts at €39 per contributor per month, billed annually. About 4,600 GitHub stars and v4.2.0 on Nov 1. For anyone eyeing GRC analyst roles, a self-run assessment of your home lab is a portfolio piece hiring managers can follow.

Listing updates

Checked on Nov 4, 2026 against official pages and release notes.

  • AiSOC: v22.0.0 (Nov 4) fixes seven security advisories in its approval and authorization code: two critical, four high and one medium. One critical bug let an approver with no tenant approve another tenant's actions; the other accepted unsigned Slack and Teams approval replies. Three fixes refuse calls that used to work (API keys can no longer enroll sign-in factors, tenant admins lose the deployment-wide tenant pages, and viewers can no longer run playbooks), so read the release notes before you upgrade. If you run AiSOC in a home lab, update now.
  • Security Onion: 3.4.0 (Nov 2) adds Agentic AI Automations for Security Onion Pro users and updates Suricata to 8.0.8, Zeek to 8.0.11 and Elasticsearch to 9.4.8. The core platform stays free; Onion AI and the new automations are Pro features. Security Onion 2.4 reached end of life on Oct 1, 2026.

Category changes

Checked, not listed

  • safeagents (Hugging Face, Apache-2.0): a local proxy that blocks dangerous tool calls between a coding agent and its model. About 70 stars a week after its repo appeared, and we already list HOL Guard and Failproof AI for this job.
  • pentest-ai (MIT, v1.6.0 Nov 3) and Decepticon (Apache-2.0): active AI pentest agents, but we already list several.
  • nono (Apache-2.0): agent sandboxing that overlaps Strands Box.
  • PagerDuty Paige (GA Nov 3): an SRE agent inside PagerDuty's paid platform, sold to existing customers.