HOL LogoGuard

Explore HOL

  • HOL home
  • AI agent registry
  • AI plugins
  • Open standards
  • HOL members

Guard product

  • Guard overviewLocal security and control for AI agents and the tools they use.
  • FeaturesRuntime protection, policy routing, review, and evidence.

Explore 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
  • Gemini 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.

Community

  • ReleasesVersion history, shipped changes and upgrade notes.
  • ContributorsThe people and contributions behind HOL Guard.
  • AffiliatesShare Guard with your audience and earn from referrals.
  • SponsorKeep agent security open: sponsor a project, place a banner, or fund a security initiative.
PricingEnterpriseOpen AppInstall Guard
  1. Guard
  2. Security
  3. CVEs
  4. CVE 2026 76850 lmdeploy remote code execution via unsafe pickle
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
Guard
  • Guard Overview
  • Releases
  • Contributors
  • Install Guard
  • Pricing
Docs
  • Documentation Index
  • Developer Hub
  • API Reference
  • Root OpenAPI
  • Registry OpenAPI
  • Run in Postman
  • Standards
  • Submit ERC-8004 Contract
  • Feature Your Agent
Best Plugins
  • Browse Plugins
  • Plugin Launches
  • Best Claude Plugins
  • Best Codex Plugins
  • Best Grok Plugins
  • Best Kimi Plugins
  • Best DeepSeek Plugins
  • Best Antigravity Plugins
  • Best MCP Servers
  • Best Cursor Plugins
  • Best OpenCode Plugins
Best Agents
  • Best ERC-8004 Agents
  • Best Virtuals Agents
  • Best MCP Servers
  • Best A2A Agents
  • Best x402 Payable
  • All Categories
Community
  • Telegram
  • X
More
  • About HOL
  • Contact
  • Blog
  • GitHub
  • Privacy
  • Terms of Service
Settings

Copyright © 2026 HOL DAO LLC. All rights reserved.

Back to active CVEs
Critical · CVSS 9.3CVE-2026-76850

LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector

Answer in brief

CVE-2026-76850 records a Critical severity (CVSS 9.3) vulnerability in LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector. The current sources do not mark it as known exploited. The current feed maps InternLM/lmdeploy (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 Aug 19, 2026Updated Sep 24, 2026Source checked Oct 3, 2026First seen by HOL Aug 19, 2026Material review Sep 24, 2026
Upstream Advisory

Key facts

Risk
Critical · CVSS 9.3
Exploitation
Not marked as known exploited
Affected software
1 mapped package or product
Fix availability
Available

Why this deserves its current priority

CVSS is 9.3. 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 InternLM/lmdeploy (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
PackageAffected rangeFixed version
InternLM/lmdeploygeneric>=0.9.2 <0.16.00.16.0

Recommended response

  1. 1Check inventory. Check lockfiles and deployed manifests for InternLM/lmdeploy.
  2. 2Review the reported fix. Update InternLM/lmdeploy to 0.16.0 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

  1. Published upstream

    Aug 19, 2026

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

    Sep 24, 2026

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

    Aug 19, 2026

Sources and claim methodology

  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • GitHub security advisorygithub.com
  • Source referencevulncheck.com
Upstream source description

LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.

Quoted source text, attributed separately from HOL analysis.

Related CVEs

  • WP Ultimate Review <= 2.4.3 - Unauthenticated Arbitrary Shortcode Execution via 'xs_reviw_summery' Parameter (Split-Shortcode / Late-Registered Shortcode)Same generic ecosystem
  • WordPress Kirki plugin <= 6.3.1 - Arbitrary Code Execution vulnerabilitySame generic ecosystem
  • WordPress Unlimited Elements For Elementor (Free Widgets, Addons, Templates) plugin <= 2.0.20 - Cross Site Scripting (XSS) vulnerabilitySame generic ecosystem
  • WPMobile.App <= 11.84 - Unauthenticated Stored Cross-Site Scripting via '/android_json/search/<value>/0' Path SegmentSame generic ecosystem
  • WP Ultimate Review <= 2.4.3 - Authenticated (Subscriber+) Arbitrary Shortcode Execution via 'xs_reviw_summery' ParameterSame generic ecosystem
  • WPC Estimated Delivery Date for WooCommerce <= 4.0.1 - Reflected Cross-Site Scripting via 'rule_data' ParameterSame generic ecosystem

Record context

Vulnerability class
Deserialization
EPSS
Not reported
CWE IDs
CWE-502
Source
CVE List V5
Source checked
Oct 3, 2026
References
7 linked sources
Open source record