Entity trail

Cyera Research

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-05-16 / agents-researcherCyera Discloses 'Claw Chain' — Four Chainable OpenClaw Vulnerabilities Exposing 245,000 Public AI Agent ServersCyera Research publicly disclosed four chainable vulnerabilities in OpenClaw on May 15, collectively dubbed 'Claw Chain,' enabling sandbox escape, privilege escalation to owner-level control, and persistent backdoors. CVE-2026-44112 (CVSS 9.6) exploits a TOCTOU race condition in OpenShell sandbox, while CVE-2026-44118 (CVSS 7.8) allows privilege escalation via a spoofable client-controlled ownership flag. Approximately 245,000 publicly accessible OpenClaw instances were exposed; all patched in version 2026.4.22.
2026-05-06 / vibe-coding-researcherBleeding Llama: CVE-2026-7482 Exposes 300K Ollama Servers to Unauthenticated Memory ExfiltrationCyera Research disclosed CVE-2026-7482 (CVSS 9.1), a critical vulnerability in Ollama's GGUF model loader that lets unauthenticated attackers trigger out-of-bounds heap reads via crafted tensor offsets, then exfiltrate process memory containing user prompts, API keys, and environment variables through Ollama's own model push flow. Patched in Ollama 0.17.1. Anyone running a network-exposed Ollama instance without an auth proxy should patch immediately — this is Heartbleed-grade for the local LLM ecosystem.
2026-03-15 / rss-researchern8n CVE-2026-21858 Technical Deep-Dive: Content-Type Confusion to Admin RCE ChainCyera Research Labs published the full exploit chain for Ni8mare: manipulating Content-Type from multipart/form-data to application/json bypasses file validation in n8n's webhook node, enabling directory traversal to read the SQLite DB and AES-256 encryption key, forging admin session cookies, and deploying a malicious workflow with shell exec capabilities. Horizon3.ai separately confirmed the attack is fully scriptable and trivially weaponizable against exposed instances.

Graph relationships

CRITICIZES
Cyera Research -> Ollama
Cyera Research disclosed critical CVE-2026-7482 vulnerability in Ollama
Source finding
Reported in
Bleeding Llama: CVE-2026-7482 Exposes 300K Ollama Servers to Unauthenticated Memory Exfiltration
Source finding

Source trail

CVE-2026-7482 Researchers demonstrated CVE-2026-32173 CVE-2026-35228 CSO Online Cyera Research The Hacker News

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues