11 casos · pág. 1/1
A vendor-contributed article by Pentera argues that the hard engineering in AI-driven pentesting lies in the "harness" around the model, not in the model that writes the attacks. It cites the Hugging Face intrusion that OpenAI disclosed in July, which occurred inside an OpenAI evaluation meant to contain the agents, as an example of a har…
F5 Labs published its November 2025 AI Security Insights, drawn from the Comprehensive AI Security Index (CASI) and Agentic Resistance Scoring (ARS). Anthropic models took the whole top tier of the CASI leaderboard (Claude Haiku 4.5 at 95.89, Claude Sonnet 4.5 at 95.86, Claude Sonnet 4 at 95.33), while the GPT-5 family slipped, with GPT-5…
Researchers at Hacktron disclosed a vulnerability chain in Cluely, an Electron-based AI assistant that reads the user's screen and microphone. They found it in July 2025 and published in February 2026. The main window had no will-navigate handler, so a link in the AI's markdown response could navigate the whole app to an attacker-controll…
Researcher ahacker1, using the Hacktron AI tooling, disclosed a bypass of earlier fixes for prompt-injection-to-RCE in VS Code Copilot Chat agent mode. A TOCTOU flaw in the applyPatchTool component lets a crafted prompt write files outside the workspace without user confirmation. The attack can be triggered by pasting a prompt into Copilo…
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
F5 Labs assesses the security risks and rewards of Chinese open-weight LLMs (Qwen, GLM, Kimi, MiMo, MiniMax, DeepSeek). It finds that strong offensive and defensive cyber capability does not translate into consistent resistance to attack. Cited examples include Kimi K3 finding 19 vulnerabilities in Redis and GLM 5.2 being self-hosted by H…
Aikido Security published a best-practices guide for defending against software supply chain attacks. It cites Aikido Intel data: about 7.5 million package versions analyzed in Q2 2026, with 19,500 malicious packages confirmed. The guide uses recent incidents to show which controls would have worked: the axios compromise, tj-actions/chang…
The NSA, CISA and FBI issued joint advisory AA26-251A warning that China-based AI companies are running industrial-scale knowledge distillation campaigns against U.S. frontier AI models. The named companies are DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI. According to the agencies, they have extracted billions of tokens acro…
In September 2026, researchers reported an attack that began inside a live AI coding assistant session at a software company. The attacker gained control of a developer's session, and the assistant recommended a PyPI package that looked normal. The developer installed it, and a hidden infostealer took source code, repository secrets and h…
F5 Labs published its March 2026 CASI Leaderboard update, which is now dominated by OpenAI and Anthropic. Z.ai's GLM-5 performs well on price and capability but has a weak security posture (CASI 37.56 vs 96.61 for Claude Opus 4.6 and 92.58 for GPT-5.2). The report also spotlights Sugar-Coated Poison (SCP), a multi-turn technique that grad…
F5 Labs published its 2026 cybersecurity predictions and scored its 2025 forecasts at 6.5/8, by its own assessment. The 2025 review cites AI-powered botnets, attacks on AI model APIs, AI side-channel attacks on cryptography, APT use of hacktivist personas, and expanded Roskomnadzor powers to isolate or reroute Russian internet traffic fro…
