DAILY DROP · NOV 6, 2026

Today's drop: 2 new tools, 1 listing update

The directory now lists 141 hand-checked tools. New today: CVE Intel, a free, open-source desktop app (also a CLI and MCP server) that tells you which vulnerabilities matter using 41 public sources such as CISA KEV and EPSS, and Grim Prompter, a free threat-modeling skill that has Claude Code or Codex build a threat model traced to your code. Updated: AiSOC (v22.2.0 reliability fixes). AI for IT & Cybersecurity grows to 55 tools. Pricing only where the official page states it.

Previous drop: Nov 5, 2026 →

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

New in the directory 2

Browse all 141
Tool
Category
Price
Status
Link
CVE IntelFree, open-source desktop app for vulnerability triage, written in native Rust, that is also a CLI, REST API and MCP server (41 tools) in one executable. Give it a CVE ID, a project folder, lockfile or SBOM, a container image, the software on your own computer, your own domains, or a suspicious IP, hash or domain; it queries up to 41 public sources (NVD, CISA KEV, FIRST EPSS, ENISA EUVD, OSV, GitHub Advisories and more, many with no API key) and returns a 0-100 risk score, whether attackers are already exploiting it, the evidence behind each signal and what to do next. Reads and writes CycloneDX SBOMs and keeps a decision ledger. An optional Ask AI assistant runs on a small local model (Qwen 2.5 3B via llama.cpp by default, about 6 GB RAM) or Ollama/LM Studio; remote providers are opt-in. Installers for Windows, macOS and Linux (not code-signed yet, so expect a first-launch warning). About 135 GitHub stars; v0.3.27 shipped Nov 2, 2026 (Arch Linux package scanning).
Price Free and open source (MIT or Apache-2.0)
FREE TIERchecked 11/06
Grim PrompterFree, open-source (MIT) threat-modeling skill for AI coding agents from Jim Manico, the application security trainer and longtime OWASP contributor. Link its threat-model skill into Claude Code or Codex (or add a snippet to AGENTS.md for any other agent), then ask for a quick model, a full six-stage deep analysis, one method such as STRIDE per element, or a review of how a branch changes an existing model. 36 architecture workflows and 29 method and analysis prompts; the runbook requires read-only inspection with file-and-line citations, and builds, tests, installs or network access need your explicit approval. Results land in a threat-model/ folder as a Markdown report plus JSON you can diff later. Also covers MCP servers and agent tools (credentials, permissions, tool-description poisoning). About 375 GitHub stars about a week after release (Oct 28, 2026). Output is a draft for you to review, not a security certification.
Price Free and open source (MIT); you pay for your own coding agent
FREE TIERchecked 11/06

Why these two

  • CVE Intel answers the question every IT and security team asks about a CVE: does it affect us, and do we patch now? Give it a CVE ID, a project folder or lockfile, an SBOM, a container image or the software installed on your own computer, and it checks up to 41 public sources (NVD, CISA KEV, FIRST EPSS, ENISA EUVD, OSV, GitHub Advisories and more, many without an API key) and returns a 0-100 risk score, whether the bug is already exploited, the evidence and a next step. It is one Rust executable that is a desktop app, CLI, REST API and a 41-tool MCP server, with an optional Ask AI assistant on a small local model. Free under MIT or Apache-2.0, installers for Windows, macOS and Linux (not code-signed yet), about 135 GitHub stars and frequent releases (v0.3.27 on Nov 2). It is a hands-on way to learn vulnerability management, a core skill for SOC and sysadmin roles.
  • Grim Prompter comes from Jim Manico, a well-known application security trainer and OWASP contributor. It is a skill for Claude Code, Codex or any agent that reads AGENTS.md: ask for /threat-model and the agent inspects your repo read-only, maps trust boundaries, threats and existing controls, and writes a report with file-and-line citations plus JSON you can diff when the code changes. 36 architecture workflows (web, API, MCP servers and more) and 29 method prompts such as STRIDE per element. Free under MIT; about 375 GitHub stars about a week after its Oct 28 release. Treat the output as a draft to challenge, not a certification. We already list scanners like Semgrep and Codex Security that find bugs; Grim Prompter is the design-level review that comes before them.

Listing updates

Checked on Nov 6, 2026 against official pages and release notes.

  • AiSOC: v22.2.0 (GitHub release Nov 5, 9:43 PM ET) follows two security releases with reliability work. A fusion worker that lost its message broker (for example at a cold boot) used to stay down until someone restarted the container; it now retries with backoff and readiness recovers on its own. A new CI check requires every connector to read its full poll window, after six connectors shipped a paging bug that could miss alerts; the project lists about 20 more connectors it could not yet confirm against vendor docs. If you run AiSOC, updating is worthwhile, and the v22.1.0 advice still stands: set your own SECRET_KEY.

Category changes

Checked, not listed

  • kodeblue (Apache-2.0, ~66 stars): a SOC and incident-response agent for Linux servers; promising but very new, and we already list AiSOC and Wazuh.
  • pwner (AGPL-3.0, ~78 stars): an autonomous network pentest agent; we already list several AI pentest agents.
  • AgentPolicy (Apache-2.0, v0.1.0 Nov 1): a fail-closed policy engine for agent tool calls; overlaps HOL Guard and Failproof AI.
  • Trim Reaper and Dread Ledger: Jim Manico's companion skills for dependency reduction and security logging; we list Grim Prompter as the most broadly useful of the three.