All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.
A security firm created a fake AI agent skill (a bundle of instructions that agents load and follow) that bypassed all security scanners and reached approximately 26,000 agents by exploiting a structural weakness: scanners only check the skill's initial package, but attackers can change the external webpage the skill points to after it passes review. The fake skill appeared legitimate through inherited GitHub credibility and targeted ads, demonstrating that current trust signals and scanning tools fail to catch sophisticated attacks.
Fix: Treat skills as software, not text, by vetting what a skill points to externally, not just what ships inside it. Route new skills through a single source you control and re-check them when anything changes since a clean result at install does not stay clean if the skill connects to a link someone else can edit. Additionally, pin versions, hold agents to the least privilege (minimum access needed to function), and assume any external instruction an agent fetches runs with the agent's full access level.
The Hacker NewsSony's new AI Camera Assistant, featured in the Xperia 1 VIII phone, produces poor quality photos according to a review. The AI tool, which is meant to help improve photography, performs worse than similar features like Google's Camera Coach found on Pixel phones.
Advanced AI models offer benefits like stronger cybersecurity and faster scientific discovery, but they also pose safety and security risks if their capabilities aren't properly understood or safeguarded. To address this, OpenAI helped found the Appia Foundation (an organization hosted by the Linux Foundation), which will create open technical standards and assessment criteria that allow different organizations and governments to evaluate and trust AI systems using a shared language and consistent methods.
Traditional security detection tools were not designed to handle AI-era threats, which move faster and create new attack surfaces through prompt injection (tricking AI by hiding instructions in its input), coding agents accessing codebases, and cloud-native AI services. The document argues that manual investigation by security analysts is too slow when the time between initial access and damage can shrink to minutes, requiring instead real-time detection with automated investigation and containment rather than human-driven responses.
Microsoft discovered that two unrelated attackers were operating inside the same victim network simultaneously, each hiding the other's presence and making it harder to understand the full scope of the attack. The initial intrusion exploited vulnerabilities in on-premises SharePoint servers (software used by organizations to manage documents and content), with one attacker (Storm-2603) deploying ransomware (malicious software that locks up files and demands payment) while a second attacker used different tools and methods for data theft. Microsoft's investigation team separated the two attack chains by correlating (comparing) data from multiple sources, then identified a second organization that had also been compromised by the same attackers.
Australian politicians are raising concerns that the country is unprepared for AI development, with calls to prevent large tech companies from using Australian content to train AI models (teach AI systems by feeding them data) and to pause approval of new datacenters until proper regulations exist. The debate reflects worry that AI is advancing faster than government safeguards can keep up.
Modern cybersecurity strategy has a fundamental contradiction: organizations claim to expect breaches will happen, but still focus almost entirely on prevention rather than preparing to survive them. The article argues that the goal of cybersecurity should shift from pure prevention to organizational resilience, meaning companies must design systems that can continue operating, recover quickly, and restore critical functions even after a breach occurs.
Omio, a travel platform connecting millions of travelers with transportation options, is using conversational AI (AI that understands natural language questions from users) to let people book trips by simply describing where they want to go, rather than searching through websites. The company launched this capability through ChatGPT in 2023 by connecting OpenAI's language models directly to its real-time transportation data, and it is now using similar AI tools internally to help engineers and other employees work more efficiently.
Fix: The source discusses initiatives to build standards and governance frameworks rather than fixing a specific vulnerability. Explicitly mentioned approaches include: developing open, modular specifications through Appia, establishing a strengthened Center for AI Standards and Innovation (CAISI), creating a 'shared playbook for trustworthy third-party evaluations' that requires disclosure of the system tested, tool access, evaluation methods, available resources, and validation checks, and implementing OpenAI's Preparedness Framework and Frontier Governance Framework to operationalize risk management practices around risk assessment, model reporting, security controls, and incident response.
OpenAI BlogThis newsletter roundup covers several AI and tech developments, including ASML's $400 million lithography machine (a tool that uses extreme-ultraviolet light to pattern features on computer chips) that dominates global chipmaking, tensions between Anthropic and the US government over export controls on an AI coding model, and Meta pausing an AI training program that tracked workers' keystrokes after sensitive data was leaked.
Some parents and education experts are concerned that using AI chatbots (software programs that simulate conversation) like Google Gemini in classrooms may discourage independent thinking, with critics arguing there is little evidence these tools actually help students learn. One parent in New York objected to an assignment where students used an AI chatbot for feedback instead of discussing improvements with peers or teachers.
Agentic AI (artificial intelligence systems that can independently execute tasks without human intervention at each step) represents a major shift in cybersecurity threats because it allows attackers to move from using AI as a drafting tool to using it as an autonomous weapon that can plan and carry out attacks on its own. This technology lowers the barrier to entry for unskilled attackers while dramatically speeding up campaigns from experienced ones, creating a broader threat landscape where attackers can now operate at speeds and scales that were previously impossible.
OpenAI expanded its Daybreak cybersecurity initiative to focus on fixing vulnerabilities faster rather than just finding them, arguing that AI models have made vulnerability discovery so fast that security teams are overwhelmed by the volume of findings. The company released an updated Codex Security plugin (a tool that scans code and generates patches) and GPT-5.5-Cyber (a specialized AI model for security work), along with Patch the Planet, a program that deploys security experts to help open source projects validate and fix vulnerabilities.
Fix: OpenAI released an updated Codex Security plugin that 'can scan entire codebases, trace attack paths, construct threat models, validate findings, generate patches, and export results into existing vulnerability management pipelines via SARIF files and CodeQL queries.' The company also launched GPT-5.5-Cyber, described as capable of 'sustain[ing] analysis across large codebases, assess[ing] whether vulnerable code is actually reachable, and carry[ing] work through to patch development and testing.' Additionally, Patch the Planet deploys expert security researchers to work with open source project maintainers to handle 'validation, deduplication, and patch development.'
SecurityWeekAnthropic's Fable 5 model was successfully jailbroken (tricked into bypassing its safety restrictions) shortly after its release, despite the company's claims that it had been thoroughly tested for security. The source criticizes overconfident security statements, noting that even rigorous testing cannot guarantee that vulnerabilities will not be discovered.
OpenAI launched Patch the Planet, a program that uses AI to find and fix vulnerabilities (security flaws) in widely-used open-source software (code that anyone can access and modify) with help from cybersecurity firm Trail of Bits. The program combines AI-assisted vulnerability research with human review to develop tested fixes and coordinate their disclosure through existing project channels. The initiative has already identified hundreds of security issues and merged dozens of patches across projects like Python, Go, and cURL.
Fix: The source describes the Patch the Planet program itself as the mitigation approach: AI-assisted vulnerability research is used alongside human review by Trail of Bits engineers who filter out false positives and duplicate reports before sending findings to maintainers. Additionally, the source recommends that CISOs implement governance controls before deploying AI-assisted vulnerability research, including what one analyst calls a 'Safety Relevance Layer' that requires every AI-generated finding to pass automated verification with dynamic proof-of-concept validation and strong false-positive filtering before reaching a human analyst, plus predefined escalation paths and notification timelines for disclosed flaws in external dependencies.
CSO OnlineOpenAI released an improved GPT-5.5-Cyber model and updated Codex Security plugin (a tool for finding and fixing code problems) to help security defenders find and patch software vulnerabilities more quickly. The company is also launching Patch the Planet, a partnership with Trail of Bits to secure open-source projects, because AI models are now finding vulnerabilities faster than developers can fix them, shifting the bottleneck from discovery to patching.
Fix: OpenAI is providing the improved GPT-5.5-Cyber model to trusted defenders as part of the Daybreak initiative. The updated Codex Security plugin allows developers to run deep scans, generate reports with severity levels and affected code locations, generate codebase-specific patches for review, and facilitate patch generation at scale. The Patch the Planet initiative lets security engineers review and validate findings, work with projects to develop patches and tests, and help build reusable vulnerability discovery workflows.
The Hacker NewsFive Eyes cybersecurity agencies (US, UK, Canada, Australia, New Zealand) warn that threat actors are increasingly using AI to bypass security defenses, with capabilities advancing in months rather than years, so organizations must urgently update their cyber risk strategies. They recommend that business leaders treat cybersecurity as core business risk, get security fundamentals right, use AI deliberately to strengthen defenses, and take practical actions like reducing attack surface, accelerating security patches, and preparing breach response plans. However, some experts criticize the guidance as too generic and lacking specific advice on AI-related risks.
Ubiquiti UniFi OS has a vulnerability where it doesn't properly check user input, allowing someone on the network to perform command injection (running unauthorized commands on the system). This vulnerability is currently being exploited by attackers in real attacks.
Fix: Apply mitigations according to vendor instructions and follow CISA's BOD 26-04 guidance on prioritizing security updates. If mitigations are unavailable, discontinue use of the product. Organizations must evaluate whether their systems are exposed to the internet and ensure they meet BOD 26-04 patching requirements by the due date of 2026-06-26. See the Ubiquiti Security Advisory Bulletin 064 for specific vendor guidance.
CISA Known Exploited VulnerabilitiesUbiquiti UniFi OS has a path traversal vulnerability (a flaw that lets attackers access files outside their intended directory) that could allow someone on the network to read and modify system files to gain unauthorized account access. This vulnerability is currently being actively exploited by attackers in the wild.
Fix: Apply mitigations according to vendor instructions and follow CISA's BOD 26-04 guidance for prioritizing security updates based on risk. If mitigations are unavailable, discontinue use of the product. Organizations must evaluate each system's internet exposure and ensure adherence to BOD 26-04 patching guidelines by the due date of June 26, 2026. Refer to the Ubiquiti Security Advisory Bulletin 064 for specific patch details.
CISA Known Exploited VulnerabilitiesLantronix EDS5000 devices contain a code injection vulnerability (a flaw that lets attackers insert malicious commands into the system) in the username parameter that allows attackers to execute arbitrary OS commands (any commands they want) with root privileges (the highest level of system access). This vulnerability is currently being actively exploited by real attackers.
Fix: Apply mitigations in accordance with vendor instructions. Follow CISA's BOD 26-04 (Prioritizing Security Updates Based on Risk) guidance, which includes patching timelines and evaluating internet exposure. If mitigations are unavailable, discontinue use of the product. See vendor firmware updates at https://ltrxdev.atlassian.net/wiki/spaces/LTRXTS/pages/2538438657/Latest+Firmware+for+the+EDS5000+series+EDS5008+EDS5016+EDS5032 and CISA BOD 26-04 guidance at https://www.cisa.gov/news-events/directives/bod-26-04-prioritizing-security-updates-based-risk.
CISA Known Exploited VulnerabilitiesUbiquiti UniFi OS has an improper access control vulnerability (a flaw that fails to properly check whether a user is allowed to perform an action) that could let someone already on the network make unauthorized changes to the system. This vulnerability is actively being exploited by attackers.
Fix: Apply mitigations in accordance with vendor instructions, following CISA's BOD 26-04 (Prioritizing Security Updates Based on Risk) guidance. If mitigations are unavailable for cloud services, discontinue use of the product. Organizations must evaluate each asset's internet exposure and ensure adherence to BOD 26-04 patching guidelines by the due date of 2026-06-26. Refer to the Ubiquiti Security Advisory Bulletin 064 at https://community.ui.com/releases/Security-Advisory-Bulletin-064-064/84811c09-4cf4-42ab-bd61-cc994445963b for specific vendor instructions.
CISA Known Exploited Vulnerabilities