Blog
Insights, updates, and deep dives on AI agents, decentralized standards, and the future of HOL.
F5 BIG-IP APM OAuth RCE hits CISA KEV
How to fix CVE-2026-94127: install F5 Hotfix-BIGIP-21.1.0.2.0.30.22-ENG, 17.5.1.9.0.160.12-ENG, or 17.1.3.5.0.41.14-ENG for your train
BREAKING: CVE-2026-94545 Next.js next/og ImageResponse RCE (GHSA-vcvr-r3jv-pc5j)
How to fix CVE-2026-94545: upgrade next to 16.3.6 (15.5.26 hardening if you stay on 15.x)
HOL Guard
Your Erlang TLS 1.3 client can trust a server with no certificate
How to fix CVE-2026-89422: upgrade Erlang/OTP to 29.1.1, 28.5.0.7, or 27.3.4.18
HOL Guard
Temporal write access can run shell on your Worker Service host
How to fix CVE-2026-89139: upgrade Temporal Server to 1.31.3 or 1.30.7
HOL Guard
BREAKING: OpenShift console Devfile API lets anyone SSRF your cluster
How to fix CVE-2026-75885: upgrade OpenShift console when Red Hat ships the errata
HOL Guard
BREAKING: WordPress comment XSS lets strangers plant script (7.1.1)
How to fix CVE-2026-93485: upgrade WordPress to 7.1.1
HOL Guard
Aborted multer uploads still fill the disk after the 5038 fix
How to fix CVE-2026-88932: upgrade multer to 2.4.0
HOL Guard
BREAKING: Unbound DNSKEY digest overflow can RCE your resolver (1.26.1)
How to fix CVE-2026-81642: upgrade Unbound to 1.26.1
HOL Guard
Hidden command in Claude Code: base64 piped to sh
Chat looked short. Claude Code packed a hidden command in base64 and piped decode to sh. HOL Guard froze it. Inbox: Allow just this once or Keep blocked.
HOL Guard
Keep a Codex Task on Track Through Compaction with Context Guard
A practical Context Guard walkthrough: define requirements, compact a Codex task, recover the checklist, and verify the finished document.
ScreenConnect client file runs hit CISA KEV
How to fix CVE-2026-84869: upgrade ScreenConnect to 26.6.5 or later, then reinstall host clients and update access agents
HOL Guard
Self-managed GitLab: unauth commits API file read hits CISA KEV
How to fix CVE-2026-85706: upgrade GitLab to 19.1.8 / 19.2.6 / 19.3.2
HOL Guard
Your agent tried to ship your AWS keys
You left Claude Code running. It tried to send your AWS keys to a website you never opened. Guard froze it: Allow just this once, or Keep blocked.
HOL GuardHOL Guard research desk
Security research for the AI agent era
Threat guides and evidence dossiers on prompt injection, MCP tool poisoning, slopsquatting, and the attacks shaping how teams ship code with agents.
Prompt injection
How hidden instructions trick coding agents into unsafe work.
Read the researchEvergreen guideMCP security
Tool poisoning, overbroad permissions, and shadow MCP servers.
Read the researchNew dossierSlopsquatting and package hallucination
Slopsquatting is the supply-chain attack in which attackers register package names that AI models reliably hallucinate; when an agent writes an import for a package that never existed, the attacker’s registered code installs instead.
Read the researchNew dossierMalicious extensions and marketplace fraud
Malicious extensions and marketplace fraud place trojanized editor extensions, plugins, or CI actions inside trusted marketplaces, harvesting source code, prompts, and credentials from every developer who installs them.
Read the research