Researchers Show Copilot and Grok Can Be Abused as Malware C2 Proxies

Cybersecurity researchers have disclosed that artificial intelligence AI assistants that support web browsing or URL fetching capabilities can be turned into stealthy command-and-control C2 relays, a technique that could allow attackers to blend into legitimate enterprise communications and evade...

Sparse Autoencoders Are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering CC-Delta, an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without...

GitLab 17.8 < 18.3.6 / 18.4 < 18.4.4 / 18.5 < 18.5.2 (CVE-2025-6945)

The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - GitLab has remediated an issue in GitLab EE affecting all versions from 17.8 before 18.3.6, 18.4 before 18.4.4, and 18.5 before 18.5.2 that could have allowed an authenticated attacker to leak sensiti...

CVE-2026-25805

Zed is a multiplayer code editor. Prior to 0.219.4, Zed does not show with which parameters a tool is being invoked, when asking for allowance. Further it does not show after the tool was being invoked, which parameters were used. Thus, maybe unwanted or even malicious values could be used withou...

Manipulating AI memory for profit: The rise of AI Recommendation Poisoning

That helpful "Summarize with AI" button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used for promotional purposes, a technique we call AI Recommendation Poisoning. Companies are embedding...

Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI

Large Language Model LLM applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated context--that provide cryptographically verifiable provenance acros...

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

CVE-2026-24887

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

CVE-2026-24053

Claude Code is an agentic coding tool. Prior to version 2.0.74, due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the...

Microsoft SDL: Evolving security practices for an AI-powered world

As AI reshapes the world, organizations encounter unprecedented risks, and security leaders take on new responsibilities. Microsoft’s Secure Development Lifecycle SDL is expanding to address AI-specific security concerns in addition to the traditional software security areas that it has...

GHSA-MHF6-PP52-8WQJ Moodle Cross-site Scripting (XSS) vulnerability

A flaw was found in Moodle. This Cross-site Scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

Moodle Cross-site Scripting (XSS) vulnerability

A flaw was found in Moodle. This Cross-site Scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

Cross-site Scripting (XSS)

Overview moodle/moodle is a learning platform. Affected versions of this package are vulnerable to Cross-site Scripting XSS via improper sanitization of AI prompt responses. An attacker can execute arbitrary scripts in the context of another user's session by injecting malicious HTML or JavaScrip...

CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2025-67849

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2025-67849 Moodle: moodle: cross-site scripting (xss) via improper sanitization of ai prompt responses

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

CVE-2025-67849

CVE-2025-67849 affects Moodle with an XSS flaw caused by improper sanitization of AI prompt responses. The vulnerability allows injecting malicious HTML/script into pages viewed by other users, potentially stealing sessions or manipulating the UI. Connected sources (Nessus/NASL, CVE records, OSV/...

CVE-2025-67849 Moodle: moodle: cross-site scripting (xss) via improper sanitization of ai prompt responses

A flaw was found in Moodle. This cross-site scripting XSS vulnerability, caused by improper sanitization of AI prompt responses, allows attackers to inject malicious HTML or script into web pages. When other users view these compromised pages, their sessions could be stolen, or the user interface...

Can Developers Rely on LLMs for Secure IaC Development?

We investigated the capabilities of GPT-4o and Gemini 2.0 Flash for secure Infrastructure as Code IaC development. For security smell detection, on the Stack Overflow dataset, which primarily contains small, simplified code snippets, the models detected at least 71% of security smells when prompt...

PT-2026-5959

Name of the Vulnerable Software and Affected Versions Moodle affected versions not specified Description A flaw exists in Moodle due to improper sanitization of AI prompt responses. This allows attackers to inject malicious HTML or script into web pages. Successful exploitation could lead to...