12 casos · pág. 1/1
A Chinese-speaking threat actor used AI agents coordinated through the open-source Cairn platform to attempt intrusions against more than 1,200 websites, reportedly compromising sites of over 100 companies, including Deere, SharkNinja and Cummins. Researcher Snorre Fagerland of NorForge found the activity while monitoring internet-exposed…
Microsoft published a blog post arguing that organizations should treat AI agents as a present insider threat rather than a future risk. Agents with access to critical systems can fail, be manipulated or be compromised, and their behavior can drift mid-run through prompt injection in external documents or untrusted data. Microsoft's answe…
Microsoft announced new enterprise security features on 19 October 2026 to monitor and control AI agents, treating them as potential insider threats. The centerpiece is Guardian Agents, part of Project Perception, which Microsoft introduced in June as its answer to AI-driven hacking and vulnerability-scanning systems such as Anthropic's M…
Signals Corps sampled 217 million HTTP page responses from Common Crawl and found almost 8,000 sites communicating with AI agents through HTTP headers. Most of these headers were navigational pointers, but 30 sites attempted indirect prompt injection. Of those, 22 were little more than pranks, while others could plausibly affect a visitin…
A contributed piece by Matias Madou (CTO and co-founder of Secure Code Warrior) argues that governance alone is not enough to control the security risks of agentic AI in software development. Organizations also need to know where they sit on an eight-stage AI Adoption Model. The article cites Gartner's prediction that costs of incidents d…
Microsoft announced new controls to monitor and restrict potentially rogue AI agents in enterprise environments, arguing that organizations should treat agents as insiders rather than trusted software. The capabilities extend Project Perception, the agentic security system launched in July, which was initially pitched as a defense against…
The NSA, CISA and FBI issued joint advisory AA26-251A warning that China-based AI companies are running industrial-scale knowledge distillation campaigns against U.S. frontier AI models. The named companies are DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI. According to the agencies, they have extracted billions of tokens acro…
The Mini Shai-Hulud worm from May 2026 is still infecting new GitHub repositories. SafeDep found six repositories that received malicious hook files between 20 and 24 September 2026. The cause is that all tags of the actions-cool/issues-helper GitHub Action, hijacked on 18 May 2026, still point to the malicious commit, and the payload is …
Microsoft has warned that AI agents with access to enterprise systems can be manipulated through prompt injection, compromised inputs or shifts in task context. Agents do not need malicious intent to cause harm: their ability to read corporate data, invoke tools, approve transactions and talk to other agents widens exposure once untrusted…
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
Tenable has detailed the Exchange Inspector, a three-stage vetting process for community-contributed AI agents, skills, MCP servers and playbooks listed on the open-source CyberAgents Exchange. The process was developed through Tenable's participation in the OpenAI Daybreak Defense Network. Three listings have passed so far: two from Tena…
On 4 August 2026, an npm worm published 2,234 poisoned versions across 444 package names, using credentials from twelve organisations. Affected scopes include @ornikar, @deliveroo, @onereach, @or-sdk, @servicetitan, @qlik, @picsart, and the keyv and cacheable families. The keyv, flat-cache, file-entry-cache and cacheable-request packages …
