aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI Sec Watch

The security intelligence platform for AI teams

AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.

Independent research. No sponsors, no paywalls, no conflicts of interest.

[TOTAL_TRACKED]
5,045
[LAST_24H]
6
[LAST_7D]
147
Daily BriefingFriday, June 26, 2026
>

Amazon Q Developer Executes Malicious Code From Cloned Repos: Amazon Q for VS Code had a high-severity vulnerability (CVE-2026-12957, CVSS 8.5) that allowed attackers to run arbitrary commands and steal AWS credentials by embedding malicious MCP server configurations (local processes that extend AI assistant capabilities) in a repository. The flaw occurred because Amazon Q automatically loaded and executed these configurations without verifying workspace trust or requesting user permission, giving attackers full access to the developer's environment variables and cloud credentials.

>

US Government Restricts GPT-5.6 and Mythos Releases: The Trump administration requested that OpenAI limit its GPT-5.6 rollout to government-vetted partners before a wider launch, marking the first time a US AI firm has been told to restrict model access pre-release. Anthropic's Mythos models were pulled from service for two weeks under similar restrictions before being released to approximately 100 approved companies and federal agencies, signaling a new era of government oversight for advanced AI deployments.

Latest Intel

page 1/505
VIEW ALL
01

Anthropic’s Mythos 5 is back

policy
Jun 26, 2026

Anthropic's Mythos 5 AI model has been allowed to resume operations for a limited group of organizations after a two-week negotiation with the Trump administration, according to a government letter. However, Fable 5, the public version of the Mythos-class model, remains unavailable with no clear timeline for when it might be released to the public.

Critical This Week5 issues
critical

CVE-2026-50549: Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by

CVE-2026-50549NVD/CVE DatabaseJun 25, 2026
Jun 25, 2026
>

Attackers Exploit OpenAI's Organization Invites to Impersonate Companies: Cybersecurity firms are being targeted by fraudulent OpenAI organization invitations that appear to come from legitimate companies, using OpenAI's real email infrastructure with attached payment methods to trick employees into sharing source code and internal documents. The invitations are difficult to detect despite OpenAI's domain mismatch warnings, as they leverage the platform's authentic communication channels.

>

Malware Designed to Evade LLM-Based Security Tools: Security researchers identified malware such as macOS.Gaslight (linked to North Korean threat actors) that specifically subverts AI-powered security analysis tools by causing LLM-assisted detection systems (security products that use large language models to analyze threats) to halt analysis or refuse to operate. This represents an emerging adversarial technique where malware authors are actively engineering code to bypass AI-based defenses.

The Verge (AI)
02

Trump admin allows Anthropic to release Mythos AI model to some companies, government agencies: Reports

policy
Jun 26, 2026

The U.S. government allowed Anthropic to release its Mythos 5 AI model to about 100 companies and federal agencies after a two-week standoff, during which Anthropic had disabled access to its latest models due to export control restrictions (government rules limiting what technology can be shared internationally). The Commerce Department said the decision was made to keep America competitive in AI while protecting national security.

CNBC Technology
03

China's Zhipu is closing in on top U.S. AI models with Anthropic and OpenAI held back

industry
Jun 26, 2026

Zhipu's GLM 5.2, a Chinese open source AI model (a model that can be freely downloaded and modified), has achieved performance comparable to top U.S. models like Anthropic's Opus 4.8 while costing significantly less, making it attractive to companies concerned about AI spending. Unlike proprietary models from OpenAI and Anthropic that face government restrictions, GLM 5.2 can be run on companies' own servers without risk of being revoked, positioning open source AI as a more reliable and cost-effective alternative for enterprise use.

CNBC Technology
04

What happened after 2,000 people tried to hack my AI assistant

securitysafety
Jun 26, 2026

A researcher ran a public challenge where 2,000 people attempted to hack an AI assistant by sending emails containing prompt injection attacks (tricks to make an AI ignore its safety rules and reveal secrets). After 6,000 total attempts, nobody successfully leaked the system's secrets, suggesting that modern AI models are becoming more resistant to these attacks through better training.

Simon Willison's Weblog
05

Cybersecurity firms targeted by fraudulent OpenAI organization invites

security
Jun 26, 2026

Attackers are creating fake OpenAI organizations impersonating real companies and sending legitimate-looking invitations to employees to trick them into sharing sensitive information like source code and internal documents in chats. The fraudulent invitations come from OpenAI's real email servers and include payment methods attached, making them difficult to spot even though OpenAI includes a warning that the inviter's email domain doesn't match the recipient's company.

Fix: Push Security recommends training employees to verify unexpected organization invitations and monitoring SaaS (software-as-a-service, cloud-based applications) organization memberships to reduce the risk of these types of attacks.

BleepingComputer
06

Cisco Adds NHI to Security Stack With Astrix, WideField Acquisitions

securityindustry
Jun 26, 2026

Cisco is acquiring companies called Astrix and WideField to add NHI (network hygiene intelligence, which monitors and maintains network health) to its security products. The company believes that securing AI agents (autonomous software programs that perform tasks with minimal human input) requires making identity, which verifies who or what is accessing a system, the main control system.

Dark Reading
07

GHSA-2jc5-xhx8-qj6h: fluent-plugin-opentelemetry Has Denial of Service (DoS) via Large Payloads and Decompression Bombs in `in_opentelemetry`

security
Jun 26, 2026

The fluent-plugin-opentelemetry plugin's HTTP input lacks size limits, allowing attackers to send huge or highly compressed files that consume excessive memory when decompressed, causing a DoS (denial of service, a type of attack that makes a service unavailable) attack by crashing the Fluentd logging process. If the OpenTelemetry endpoint (a connection point that accepts telemetry data) is exposed to untrusted networks, an attacker can exploit this to disrupt all log collection on the affected server.

Fix: Upgrade to v0.5.3. If immediate upgrade is not possible, restrict network access to the OpenTelemetry ingestion port (default 4318) using firewall rules to only trusted networks, or place a reverse proxy like Nginx in front of Fluentd to handle decompression and enforce strict size limits on both compressed and uncompressed request bodies before sending traffic to Fluentd.

GitHub Advisory Database
08

OpenAI hasn't held pre-IPO investor meetings or set timeline yet, sources say

industry
Jun 26, 2026

OpenAI has confidentially filed documents with the SEC (Securities and Exchange Commission, the government agency that oversees stock market listings) but has not yet held investor meetings or announced an official timeline for going public, though reports suggest a potential 2027 IPO. The company is intentionally downplaying expectations about when it will list on the stock market, with CEO Sam Altman stating that going public is a 'financing event' rather than a near-term priority.

CNBC Technology
09

CVE-2025-32394: AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agent

security
Jun 26, 2026

AutoGPT versions before 0.6.32 contain a DoS (denial of service, where a system is overwhelmed and stops working) vulnerability in its AITextSummarizerBlock component. A malicious user can input a small amount of content that causes the server to consume massive amounts of memory, exhausting resources and crashing the system, for example turning 10K of input into 50G of memory usage.

Fix: This vulnerability is fixed in version 0.6.32. Update AutoGPT to 0.6.32 or later.

NVD/CVE Database
10

Quoting OpenAI

industry
Jun 26, 2026

OpenAI announced a limited preview of three new GPT-5.6 models: Sol (high-performance), Terra (balanced), and Luna (fast and affordable), with pricing ranging from $1-$30 per million tokens depending on the model and whether the input or output is being processed. The company is starting with a limited preview for trusted partners approved by the U.S. government before making the models more broadly available, and the new models include improved prompt caching (a feature that stores frequently used inputs to speed up responses) with explicit cache breakpoints and longer minimum cache duration.

Simon Willison's Weblog
123...505Next
critical

CVE-2026-50548: Cursor is a code editor built for programming with AI. Prior to 3.0, Cursor runs agent terminal commands in a sandbox by

CVE-2026-50548NVD/CVE DatabaseJun 25, 2026
Jun 25, 2026
critical

CVE-2026-55413: ToolJet is the open-source foundation am AI-native platform for building and deploying internal tools, workflows and AI

CVE-2026-55413NVD/CVE DatabaseJun 25, 2026
Jun 25, 2026
critical

CVE-2026-12537: Improper Neutralization used in an OS Command in the container launcher in Google Gemini CLI (versions prior to 0.39.1)

CVE-2026-12537NVD/CVE DatabaseJun 24, 2026
Jun 24, 2026
high

CVE-2026-47214: Docling simplifies document processing by parsing diverse formats and providing integrations with the generative AI ecos

CVE-2026-47214NVD/CVE DatabaseJun 26, 2026
Jun 26, 2026