Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence (AI) agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, released as a preprint on August 10, 2026, tests the technique in a simulated six-agent coding
Cybersecurity researchers have disclosed details of a previously undocumented Python implant framework dubbed TWINLOOT. "TWINLOOT is a modular, PyArmor-hardened Python implant designed to operate its entire command-and-control infrastructure inside trusted Microsoft services," Ontinue said in a technical report shared with The Hacker News. "Tasking flows through SharePoint Online file
SafePal has disclosed that an authorization flaw in an order-tracking plug-in exposed the names, email addresses, shipping addresses, phone numbers, and purchase details of approximately 39,798 customers. The hardware wallet maker said all affected customers were notified individually by email on August 16 from security@safepal.com, with the subject line "[Important] Your SafePal Order
On Friday, Microsoft confirmed it has begun working on a security patch for a Defender zero-day vulnerability named "ShieldBreak." A security researcher who uses the "Nightmare Eclipse" handle disclosed this privilege escalation vulnerability after Microsoft released the August 2026 Patch Tuesday security updates. "Microsoft is aware of the reported vulnerability and is actively investigating the validity and potential applicability of these claims," a Microsoft spokesperson told BleepingComputer when asked for a statement regarding the new ShieldBreak zero-day. "Microsoft is committed to investigating security issues and updating impacted products to protect customers as soon as possible." Nightmare Eclipse described ShieldBreak as a bypass for RoguePlanet, another Defender privilege escalation flaw disclosed in June, and shared a ShieldBreak proof-of-concept (PoC) exploit that local attackers with limited permissions can use to gain SYSTEM privileges on fully patched Windows 10, Windows 11, and Windows Server systems.
GitLab has released security updates to address a critical vulnerability impacting its Community Edition (CE) and Enterprise Edition (EE) software that, under certain conditions, could allow an unauthenticated attacker to remotely modify or delete public projects and user data. The flaw, tracked as CVE-2026-19478, has been rated Critical by GitLab and assigned a CVSS score of 9.4. Released on
Cybersecurity researchers at Wiz have disclosed a new GitHub Actions workflow injection vulnerability in Snowflake's public snowflakedb/snowflake-connector-net repository that it said could be exploited through a crafted GitHub issue to execute commands in a workflow containing internal Jira credentials. The issue was present in .github/workflows/jira_issue.yml, which ran when a
The expensive attacks are not always the clever ones. This week had plenty of proof. Exposed services got hit, old bugs found fresh use, browser sessions became attack paths, and supply-chain problems kept spreading farther than the original compromise. A lot of it came down to access that was already there and defenses that assumed nobody would look too closely. So, nothing magical. Just a
Security researchers at SSD Secure Disclosure have published a two-stage exploit chain that achieves full Android kernel access on devices running Unisoc modem firmware through a VoLTE video call, with no fix from the chipset maker. The advisory, published August 17, 2026, is the second stage of a chain that began in March 2026, when SSD disclosed remote code execution in the
Cybersecurity researchers have flagged a previously undocumented Linux botnet family dubbed Evooo1Bot that derives its core functionality from the Mirai botnet source code and is equipped to turn internet-facing devices into SOCKS proxies. "While the malware reuses the DDoS engine from the publicly leaked Mirai source code, it extends the original framework with numerous capabilities, including
Claude is experiencing a major outage, with users reporting login problems and degraded performance across several Anthropic services. The incident began on August 16, 2026, at around 21:58 UTC, and is affecting Claude.ai, Claude Code, and Claude Cowork. According to Anthropic’s status page, the company first said it was investigating an issue preventing some users from authenticating to Claude.ai, Claude Code, and Claude Cowork. A few minutes later, Anthropic reported a broader service disruption involving degraded performance on Claude.ai and platform.claude.com. For users, the outage can result in problems signing in, Claude failing to load, requests not completing, or other errors when using the affected services. Anthropic’s status page currently classifies Claude.ai, Claude Code, and Claude Cowork as experiencing a major outage. Claude Console and the Claude API are currently listed as operational.
Confirm this action.
Leaving now will discard your changes.