www.ox.security Critical RCE Vulnerability in Anthropic's AI Supply Chain Protocol
Article Content
- •A critical RCE vulnerability in Anthropic's MCP threatens AI supply chains.
- •Over 30 responsible disclosures and 10+ High/Critical CVEs have been reported.
- •Organizations are advised to prioritize Software Supply Chain Security.
OX Security has identified a significant RCE-by-Design vulnerability in Anthropic’s Model Context Protocol (MCP), which poses a critical risk to organizations utilizing AI agents. This flaw has led to over 30 responsible disclosures and more than 10 High/Critical CVEs. The vulnerability stems from architectural choices in the MCP, making it a systemic issue rather than a simple patchable flaw. The ongoing risk affects any organization that integrates AI into their operations, emphasizing the need for enhanced Software Supply Chain Security. Despite efforts to address downstream impacts, the root cause remains unpatched at the protocol level. Security leaders are urged to adopt a 'Secure by Design' approach to mitigate these risks. The current status indicates that while patches have been issued, the fundamental vulnerability persists.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (3)
Following this threat?
Track Anthropic in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Continue Reading
Critical Cisco FMC Vulnerabilities Under Active Exploitation Cisco's Secure Firewall Management Center (FMC) Software has two critical vulnerabilities, CVE-2026-20079 and CVE-2026-20316, that are currently being exploited by state-sponsored and ransomware actors. CVE-2026-20079, rated 10.0 on the CVSS scale, allows unauthenticated remote attackers to bypass authentication and… 
BlueMoon Exploit Kit Targeting Chrome and Windows by Multiple State Actors A new exploit kit named BlueMoon has been rapidly adopted by at least four espionage groups, primarily linked to China, exploiting vulnerabilities in Google Chrome and Microsoft Windows. The first observed use of BlueMoon was on August 28, 2026, by the China-aligned threat actor TA412, with subsequent adoption by…