AI-driven worm reasons at runtime and self-replicates across a 33-host test network
Technical Analysis
Summary
Hide ▲
Show ▼
Researchers demonstrated a proof-of-concept AI-driven worm that reasons at runtime and self-replicates, showing adaptive host-to-host spread across a 33-host vulnerable test network. The prototype raises the risk of runtime exploit generation, fresh-advisory weaponization, and GPU-assisted propagation without a fixed exploit chain.
Related Happenings
HalluSquatting indirect prompt-injection attack on AI coding assistants
Technical Analysis
H score3
First: 08.07.2026 18:07
Last: 08.07.2026 18:07
Sources 1
About this happening:
Researchers demonstrated HalluSquatting, an indirect prompt-injection technique that can push AI coding assistants to fetch attacker-controlled resources and execute code....
HalluSquatting indirect prompt-injection attack on AI coding assistants
Technical AnalysisAbout this happening: Researchers demonstrated HalluSquatting, an indirect prompt-injection technique that can push AI coding assistants to fetch attacker-controlled resources and execute code....
Sentry agentjacking analysis shows malicious error events can trigger AI coding agents
Technical Analysis
H score38
First: 11.06.2026 12:15
Last: 11.06.2026 12:15
Sources 1
About this happening:
Researchers described Agentjacking as a new attack against AI coding agents that abuses Sentry DSNs and MCP to inject fake error data, causing agents like Claude...
Sentry agentjacking analysis shows malicious error events can trigger AI coding agents
Technical AnalysisAbout this happening: Researchers described Agentjacking as a new attack against AI coding agents that abuses Sentry DSNs and MCP to inject fake error data, causing agents like Claude...
Google GTIG analysis of adversary AI use for exploit development and attack orchestration
Technical Analysis
H score33
First: 11.05.2026 16:00
Last: 11.05.2026 16:00
Sources 1
About this happening:
Google Threat Intelligence Group published findings showing adversaries using AI for exploit development and attack orchestration, signaling that model-assisted tr...
Google GTIG analysis of adversary AI use for exploit development and attack orchestration
Technical AnalysisAbout this happening: Google Threat Intelligence Group published findings showing adversaries using AI for exploit development and attack orchestration, signaling that model-assisted tr...
Langflow CVE-2026-33017 exploitation wave
Exploitation Wave
H score50
First: 20.03.2026 12:20
Last: 20.03.2026 12:20
Sources 1
About this happening:
CVE-2026-33017 in Langflow was disclosed on March 17, 2026 as an unauthenticated RCE with CVSS 9.3, allowing arbitrary Python execution from a single HTTP requ...
Langflow CVE-2026-33017 exploitation wave
Exploitation WaveAbout this happening: CVE-2026-33017 in Langflow was disclosed on March 17, 2026 as an unauthenticated RCE with CVSS 9.3, allowing arbitrary Python execution from a single HTTP requ...
Underground AI services emerge with jailbroken APIs and MCP servers
Threat Actor Meta
H score11
First: 12.02.2026 14:45
Last: 12.02.2026 14:45
Sources 1
About this happening:
Underground AI services are emerging on marketplaces with a model that hides jailbroken commercial APIs and open-source MCP servers, expanding access to malware*...
Underground AI services emerge with jailbroken APIs and MCP servers
Threat Actor MetaAbout this happening: Underground AI services are emerging on marketplaces with a model that hides jailbroken commercial APIs and open-source MCP servers, expanding access to malware*...
Timeline
-
09.06.2026 14:59 2 articles · 1mo ago
Researchers demonstrate a self-replicating AI worm on a 33-host test network
Initial DisclosureUniversity of Toronto researchers built and tested a proof-of-concept AI-driven worm that used a locally hosted open-weight LLM to inspect exposed services, read fresh advisories, generate tailored attack logic, and self-replicate across an isolated 33-host FakeCorp network. The prototype found an average of 31.3 vulnerabilities, gained elevated access on 23.1 hosts, replicated to 20.4 hosts over seven days, and rewrote its own code to bypass local security controls; the team also showed runtime exploitation of CVE-2026-39987, CVE-2026-31431, CVE-2026-43284, and CVE-2026-43500 after the model's training cutoff.
Show sources
- Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models — thehackernews.com — 09.06.2026 14:59
- Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models — thehackernews.com — 09.06.2026 14:59