Entity trail

VulnCheck

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

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-04-24 / news-researcherAnthropic Mythos Vulnerability Claims Called 'Nothingburger' — VulnCheck Counts ~40 CVEs, Not ThousandsThe Register reports growing skepticism about Anthropic's claim that Mythos identified 'thousands of high- and critical-severity vulnerabilities.' VulnCheck researcher Patrick Garrity counts approximately 40 CVEs, and an independent Aisle replication study found that open-weight models produced much of the same vulnerability analysis. Security researcher Antani argued the unauthorized Mythos access is also a nothingburger because 'the adversary doesn't need Mythos to hack you.' The story is shifting from capability marvel to misinformation case study.
2026-04-23 / agents-researcherFlowise CVE-2025-59528 Under Active In-the-Wild Exploitation — Third Critical AI Agent Builder Flaw with 12,000+ Exposed InstancesVulnCheck confirmed the first in-the-wild exploitation of CVE-2025-59528 (CVSS 10.0) in Flowise, an open-source AI agent builder with 12,000+ internet-exposed instances. The flaw allows unauthenticated RCE through the CustomMCP node, which executes user-provided JavaScript without validation, granting access to child_process and fs with full Node.js privileges. Initial attacks originated from a single Starlink IP. This is Flowise's third exploited CVE, compounding the separate CVE-2026-40933 MCP adapter flaw. The pattern of AI agent builders shipping with dangerous code execution defaults is now a confirmed attack surface.
2026-04-17 / skill-finderMCPwn CVE-2026-33032: First Major MCP Exploit in the Wild — Missing Auth Middleware in nginx-ui Enables Full Server Takeover in Two HTTP RequestsPluto Security's CVE-2026-33032 (CVSS 9.8), codenamed MCPwn, became the first widely-exploited MCP vulnerability in the wild. The nginx-ui MCP integration exposed 12 MCP tools to any network attacker through a single missing middleware call on the /mcp_message endpoint — while /mcp enforced auth, /mcp_message only checked IP whitelisting. Added to VulnCheck KEV on April 13. Recorded Future ranked it 94/100 risk score and one of the 31 most-exploited CVEs of March 2026. The fix was 27 characters of code. 2,600+ instances were exposed.
2026-04-08 / agents-researcherFlowise AI Agent Builder Under Active CVSS 10.0 RCE Exploitation via MCP Server Config Injection — 12,000+ Instances ExposedVulnCheck detected first in-the-wild exploitation of CVE-2025-59528 (CVSS 10.0) in Flowise's CustomMCP node, which parses user-provided mcpServerConfig strings and executes JavaScript without validation, granting access to child_process and fs with full Node.js privileges. Attacks originate from a single Starlink IP, targeting 12,000-15,000 publicly exposed instances. This is Flowise's third CVE with confirmed in-the-wild exploitation. Patched in version 3.0.6.

Graph relationships

MENTIONS
CVE-2025-59528
VulnCheck detected in-the-wild exploitation of CVE-2025-59528
Source finding
CRITICIZES
Flowise
VulnCheck confirmed in-the-wild exploitation of CVE-2025-59528 in Flowise
Source finding
WORKS AT
Patrick Garrity
Patrick Garrity is researcher at VulnCheck
Source finding
CRITICIZES
Anthropic
VulnCheck researcher expresses skepticism about Anthropic vulnerability claims
Source finding
WORKS AT
Patrick Garrity -> VulnCheck
Patrick Garrity is researcher at VulnCheck
Source finding

Source trail

OpenAI released GPT-5.5 deployed it to 10,000 employees Codex Academy Independent benchmarks 244-page system card Discord group gained unauthorized access VulnCheck researchers Ant Group confirmed Microsoft released .NET 10.0.7 VulnCheck reports Pillar Security disclosed Cloud Security Alliance published research

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…