HOL LogoGuard

Explore HOL

  • HOL home
  • AI agent registry
  • AI plugins
  • AI standards
  • HOL members
  • Sponsor HOL
  • Advertise with HOL

Guard product

  • Guard overviewLocal security and control for AI agents and the tools they use.
  • FeaturesRuntime protection, policy routing, review, and evidence.
  • CIGARPoint your coding agent at the right lines and cut its token bill by about a third.

Explore Guard

  • The ChallengePlay the night shift: judge your agent against the real Guard.
  • Product previewWalk through Guard surfaces in read-only demo mode.
  • ComparisonCompare Guard with native controls and AI security vendors.

AI tools

  • All AI toolsEvery supported AI tool and how Guard applies policy to it.
  • Codex
  • Claude Code
  • Cursor
  • Antigravity CLI
  • OpenCode
  • Hermes
  • OpenClaw
  • GitHub Copilot CLI
  • Antigravity
  • Kimi
  • Grok
  • Pi / Oh My Pi
  • Zcode

Extensions

  • All extensionsBrowse command and MCP coverage with owners and stated limits.
  • Command coverageShell command protection across clouds, databases, backups, and packages.
  • MCP server coverageSee how Guard maps risk state across MCP tools and servers.
  • Core safetyThe safety floor listings that ship with Guard.
  • Data and resilienceBackup and storage command protection.
  • Cloud and infrastructureAWS, Azure, GCP, Kubernetes, and more.

Security

  • AI security hubSecurity research, advisories, and agent safety coverage.
  • AI tool securitySecurity profiles for each supported coding agent.
  • Safe labsHands-on attack simulations with safe boundaries.
  • Redacted warningsReal blocked actions with sensitive details removed.
  • AdvisoriesCoordinated disclosure reports for AI tooling.
  • Active CVEsSearch active CVEs affecting AI tooling.

Learn

  • Security guidesPractical guides for securing AI agent workflows.
  • DocsInstall, configure, and operate Guard with confidence.
  • ResearchPublished security research, benchmarks, and methodology.
  • Gauntlet benchmarkGuard tested with real coding agents: safe work runs, risky actions stop.

Community

  • ReleasesVersion history, shipped changes and upgrade notes.
  • ContributorsThe people and contributions behind HOL Guard.
  • AffiliatesShare Guard with your audience and earn from referrals.
  • SponsorFund agreed research, implementation and shared testing through the HOL Partner Program.
  • AdvertiseCompare README logo placements, previews and monthly prices, or promote a plugin or extension.
PricingEnterpriseOpen AppInstall Guard
  1. Guard
  2. Security
  3. CVEs
  4. CVE 2026 133631 flowintel insecure note variable resolution over
HOL Guard

Public security guidance for teams protecting AI harnesses, MCP servers, skills, prompts, and local tool execution.

Install Guard

AI Security

  • Prompt injection
  • MCP security
  • OWASP MCP mapping
  • Supply chain

Resources

  • Trust packet
  • Harness setup
  • Redacted warnings
  • Safe labs

Product

  • Install Guard
  • Pricing
  • Open dashboard

Get HOL Guard for your computer

HOL Guard is a free desktop app that watches what coding agents such as Claude Code, Codex and Cursor run, read and install, and asks you before anything risky happens.

  • Download for macOS
  • Windows download
  • Linux download

Free. macOS 13+ on Apple silicon, Windows x64, Linux AppImage. Other ways to install

Star HOL Guard on GitHub to download
Runs on
macOS 13 or later on Apple silicon, Windows x64 and Linux x86_64.
Price
Free. Paid plans add Guard Cloud for teams. See pricing
Where your data stays
On your computer. Guard Cloud is optional.
Token savings
55.5% to 71.3% fewer tokens across three coding agents in our CIGAR benchmark.

HOL

HOL builds open infrastructure for AI agents: HOL Guard, a directory of AI plugins and MCP servers, an AI agent registry and the open HCS standards.

  • GitHub (opens in a new tab)
  • X (Twitter) (opens in a new tab)
  • YouTube (opens in a new tab)
  • Telegram (opens in a new tab)

HOL Guard

  • What is HOL Guard
  • Features
  • Cut coding agent token costs (CIGAR)
  • Install Guard
  • Download the desktop app
  • Pricing
  • Guard for teams
  • Compare Guard
  • Release notes

Guard for your AI tool

  • Guard for Claude Code
  • Guard for Codex
  • Guard for Cursor
  • Guard for GitHub Copilot CLI
  • Guard for OpenCode
  • Guard for Pi and Oh My Pi
  • Guard for Hermes
  • Guard for OpenClaw
  • All supported AI tools

Research and security

  • Gauntlet: Guard tested with real agents
  • CIGAR token benchmark
  • Research
  • AI security hub
  • Security advisories
  • Active CVEs in AI tools
  • AI agent security guides
  • Extensions and coverage

Plugins and MCP servers

  • Browse AI plugins
  • New plugin launches
  • Best Claude Plugins
  • Best Codex Plugins
  • Best Grok Plugins
  • Best Kimi Plugins
  • Best Herdr Plugins
  • Best DeepSeek Plugins
  • Best Antigravity Plugins
  • Best MCP Servers
  • Best Cursor Plugins
  • Best OpenCode Plugins

AI agent registry

  • Best AI agents
  • Best ERC-8004 agents
  • Best Virtuals agents
  • Best A2A agents
  • Best x402 payable agents
  • Submit an ERC-8004 contract
  • Feature your agent

Developers

  • Guard docs
  • Documentation index
  • Developer hub
  • Registry API reference
  • OpenAPI spec
  • Registry OpenAPI spec
  • Run in Postman (opens in a new tab)
  • AI standards · HOL Throughline
  • Compare AI standards
  • Collaboration ideas
  • HCS specifications

Company

  • About HOL
  • Blog
  • Contribute to HOL
  • Guard contributors
  • Sponsor
  • Advertise
  • Affiliate program
  • Contact

Copyright © 2026 HOL DAO LLC. All rights reserved.

  • Privacy
  • Terms of Service
Back to active CVEs
High · CVSS 7.1CVE-2026-133631

FlowIntel Insecure Note Variable Resolution, Over-Permissive Chatbot API Access, and Credential Exposure in Process ArgumentsCVE-2026-133631

Answer in brief

CVE-2026-133631 records a High severity (CVSS 7.1) vulnerability in FlowIntel Insecure Note Variable Resolution, Over-Permissive Chatbot API Access, and Credential Exposure in Process Arguments. The current sources do not mark it as known exploited. The current feed maps flowintel/flowintel (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Nov 20, 2026Updated Nov 20, 2026Source checked Nov 20, 2026First seen by HOL Nov 20, 2026Material review Nov 20, 2026
Upstream Advisory

Key facts

Risk
High · CVSS 7.1
Exploitation
Not marked as known exploited
Affected software
1 mapped package or product
Fix availability
Available

Why this deserves its current priority

CVSS is 7.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps flowintel/flowintel (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
PackageAffected rangeFixed version
flowintel/flowintelgeneric>=0 <4.1.04.1.0

Recommended response

  1. 1Check inventory. Check lockfiles and deployed manifests for flowintel/flowintel.
  2. 2Review the reported fix. Source-reported solution: Three remediations are applied: (1) Note variable resolution now enforces an audience-based authorization check so that cross-case and cross-task references only expand when the destination case's assigned organisations can read the referenced case; (2) the chatbot API tool is restricted to an explicit allow-list of reviewed read-only and search operations, with administrative endpoints always blocked, path validation against injection and SSRF, and write operations gated behind an explicit CHATBOT_ALLOW_WRITES configuration flag; (3) AI report requests are delivered to the child process via a private anonymous temporary file on stdin instead of argv, keeping credentials and case content out of the process listing.

Evidence timeline and material changes

  1. Published upstream

    Nov 20, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  2. Source modified

    Nov 20, 2026

    Evidence: source:cvelist:source_dates:source-dates:record
  3. First seen by HOL

    Nov 20, 2026

Sources and claim methodology

  • GitHub security advisorygithub.com
Upstream source description

FlowIntel contains multiple security flaws in its note variable resolution, chatbot API tooling, and AI report generation. - Note variable references (e.g. cross-case or cross-task lookups) were resolved using the viewing user's privileges rather than the destination case's audience. An authenticated user with access to a shared or imported note could embed references to private cases, causing sensitive case data to be pulled into AI report requests, exports, and MISP sends without the referenced case's audience having granted read access. - The chatbot API tool permitted the language model to invoke any FlowIntel API endpoint, including administrative routes and state-changing GET operations, without an allow-list or path validation. An attacker who can influence the model's instructions (e.g. via untrusted case content) could induce data modification or access restricted endpoints. - AI report generation passed the Ollama bearer token and full case content as command-line arguments to a child process, exposing them in the system process table to any local user. Affected versions: FlowIntel prior to 4.1.0.

Quoted source text, attributed separately from HOL analysis.

Related CVEs

  • FlowIntel: Resource Exhaustion via Sparse CSV/JSON Table Expansion During File-to-Note ConversionSame flowintel/flowintel package
  • flowintel Case History Log Injection via Line Separator Characters in User-Authored FieldsSame flowintel/flowintel package
  • flowintel CI/CD Workflow Exposes Checkout Credentials in Docker Build CacheSame flowintel/flowintel package
  • Mang Board <= 2.4.7 - Missing Authorization to Unauthenticated Arbitrary Content Deletion via 'mode' / 'comment_pid' / 'board_pid' Parameter ConfusionAlso CWE-862
  • Pie Register <= 3.8.4.17 - Missing Authorization to Unauthenticated Administrator Role Modification via Oversized 'username' ParameterAlso CWE-862
  • WordPress Starter Templates plugin <= 4.7.11 - Broken Access Control vulnerabilityAlso CWE-862

Record context

Vulnerability class
Missing Auth
EPSS
Not reported
CWE IDs
CWE-862, CWE-284, CWE-200
Source
CVE List V5
Source checked
Nov 20, 2026
References
1 linked source
Open source record