Our latest AI Coding and Open Source Risk webinar examines what this means for security and engineering teams, drawing on data from 300 enterprise leaders. More dependencies mean more vulnerabilities to review, more remediation work, and a backlog that can quietly keep growing. Users running an affected release should move to a version outside the affected range. VulnCheck’s CVE Numbering Authority (CNA) record assigns it a CVSS v4 score of 8.7 and a CVSS v3.1 score of 8.8, with user interaction required and no attacker authentication required. There is no fix on the Windows and WSL path, according to Luz, where v0.0.34 added a Windows installation that carries a warning instead. Aikido’s test system is a single-page web application backed by a https://canadatc.com/pq-hosting-various-services-for-a-wide-range-of-clients.html GraphQL API carrying the two flaws described in the original incident.
But ASSET Research Group’s tests show agents can still combine instructions across them in the same working context, so no single fragment has to contain the whole mal… Across 6,708 public agent trajectories, the team decoded 315,320 thinking blocks. A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. There is no evidence that the technique has spread successfully in the wild, and the same paper reports that a review of archived posts from Moltbook, the social network for https://bestchicago.net/cooltisyntrix-is-an-innovative-ai-platform-for-safe-and-smart-cryptocurrency-investing.html AI agents, found no successful agent-to-agent propagation despite several attempts.
The employee followed its advice, inadvertently making a large volume of sensitive data available to unauthorized engineers for over two hours. The company said it has attempted the attack 20 times since June with a 40% success rate, and that the failures cam… Asked which build was tested, Adversa told The Hacker News the target was the Grok web chat at grok.com running Grok 4.5 Fast, and that the attack was reproduced once on August 19, 2026. “When the module loads, it locates the bundled binary, marks it executable, and launches it as a detached background process,” TrendAI, Trend Micro’s enterprise cybersecurity business, said in a report published Thursday. Your team may then need to assess vulnerabilities, licensing, maintenance, ownership, and whether that package should be there at all. The Real Problem Is What AI Adds to Your Stack AI coding itself is not the issue.
Agents
The test removed the person holding the top place and moved the user up one position. The agent booked sessions months beyond the window the site allowed. “The message, document service and redirect can therefore appear trustworthy until the browser reaches attacker-controlled infrastructure….
- And some systems turned out to be easier to break into than anyone would like to admit.
- Markey said it would address how details on recent AI incidents have only been made public in “piecemeal” fashion.
- “Of these verified vulnerabilities, more than 33,000 have so far been rated as critical- or high-severity,” Anthropic said .
- Anthropic on Friday said it’s cutting off live internet access for all its internal evaluations until further notice following the discovery of new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior and targeted real websites.
- A malicious MCP server can put one fragment in a tool description and another in a tool result; some setups also support server-initiated sampling.
- Meanwhile, Sen. Ed Markey (D-Mass.) in recent days introduced the Cybersecurity and AI Board of Investigations Act.
The company said it reported the issue to Microsoft in December 2025 and that patches shipped on August 18, 2026. The flaws, which the researchers collectively named CoSnitch , turn in part on an undocumented URL parameter that the assistant itself surfaced during testing. The tool was approved, but the AI behaved in ways nobody had anticipated.
ThreatsDay: Ransomware Affiliate Betrayal, WhatsApp RAT, Exposed Hacker Tools and 12 More Stories
The activity , per CrowdStrike Intelligence, was active from late September to early October 2026, and resulted in data exfiltration from various South Korea-based financial firms , including Shinhan Bank and Yegaram Savings Bank. Given that personal agents will reach corporate systems whether approved or not, you might be wondering what the best way is to block them. Their agents already manage their home time, and managing their work time is the next logical step. Less than a year after the first release of the open-source agent now called OpenClaw, the juggernauts are putting their weight behind the idea that each of us needs a personal assistant. Someone downloads a local model runtime, a program that runs models directly on the machine instead of sending data to an external service, because they were told not to send company data outside. A user opens a browser tab, pastes data into a chat assistant, and nothing is installed.
AI Training Critical as Governance Challenges Grow
A one-paragraph warning added to an agent’s system prompt reduced spread to near zero https://homadeas.com/vodds-online-casino-and-pragmatic-play-games-main-advantages-and-features.html across the payloads tested. Varonis Threat Labs has disclosed three vulnerabilities in Microsoft Copilot Personal that it said could allow a single click on a crafted link to silently pull data from connected apps and other information available to the victim’s Copilot session. Shadow AI is the unapproved use of AI tools Shady AI is when employees use approved AI tools in unapproved, unexpected, or poorly governed ways Shadow AI happens outside the organization’s visibility. An engineer used an approved AI agent to analyze it, but the agent posted its response publicly without approval. The incident began when a Meta employee posted a technical question on an internal forum. There is no patch, no CVE identifier, and no user-facing workaround, and the writeup does not report any exploitation in the wild.
NovaCookies Campaigns Abuse Genuine Docusign Notifications to Steal Microsoft 365 Sessions
The AI security company, which has codenamed the technique “Cryptographic Context Injection ,” said the transfer completed without a confirmation step and with no visible warning in its proof-of-concept demonstration. Cybersecurity researchers have discovered a set of trojanized npm packages that masquerade as working calendar and streak utilities but are engineered to stealthily deliver an artificial intelligence (AI)-powered Linux implant dubbed RedC2 4.0. The problem is how quickly generated code can bring new open-source components into your environment.
- The npm package known as ” tensorlake ,” a TypeScript software development kit (SDK) for Tensorlake applications, sandboxes, and cloud services, was compromised as part of a ChainDrop / Shai-Hulud supply chain attack.
- Even AI assistants are getting their own instructions hidden inside phishing messages now.
- Scroll down for all the latest news and information covering artificial intelligence
- Attack path analysis could potentially provide a solution to stop the next rogue AI agent breach according to one startup.
- This week’s full recap is worth a read, especially the bits that didn’t make the big headlines.
Each row gives an organization’s name and domain, a count of secrets exposed, a count of runs, and a label reading High or Medium. CloudSEK has published the dataset as a public lookup , searchable by name or domain and filterable by confidence. Ray is an open-source, Python-native distributed computing framework designed to scale artificial intelligence and machine learning workloads.
- Malicious code turned up in developer packages and extensions that looked harmless.
- Across 6,708 public agent trajectories, the team decoded 315,320 thinking blocks.
- “If Democrats regain control of the House, technology companies should expect increased scrutiny of AI development, safety practices, competition, content moderation, and data privacy, including a renewed push to bring technology executives before congressional committees to testify on these issues,” they wrote.
- The proposal is similar to the AI Kill Switch Act introduced in July by Rep. Ted Lieu (D-Calif.) and Rep. Nathaniel Moran (R-Texas).
- AI is helping development teams produce far more code, far faster.
- Aikido Security has published research that recreates the Australian gym-booking incident in a synthetic environment, finding that Claude Opus 4.6, running on the OpenClaw agent harness, exploited a client-side-only booking restriction in 9 of 10 runs.
Markey said it would address how details on recent AI incidents have only been made public in “piecemeal” fashion. The bill would establish an independent board with subpoena power to investigate cybersecurity incidents, including those involving AI. OpenAI has announced that it’s pausing some “internal activities” involving its upcoming artificial intelligence (AI) model Astra after an internal evaluation found it had made significant advancements in agentic coding and cybersecurity. The attack targets coding tools that connect to outside servers over the Model Context Protocol (MCP), the open standard that lets AI assistants call external tools. Two malicious LiteLLM releases sat on PyPI for about 40 minutes in March carrying credential-stealing code capable of harvesting cloud keys, SSH keys, Kubernetes tokens, database passwords, and other secrets from systems that installed them.