Help Net Security جمعه ۸ آبان ۱۴۰۵ · ۱۶:۲۳

Shufti ties AI agent actions to verified owners and permissions

Shufti launches Know Your Agent (KYA), an AI agent verification solution designed to verify autonomous AI agents acting on behalf of individuals and businesses. Agentic commerce enables AI agents to open accounts, place orders, and move funds for their owners. A business receiving one of these requests needs to know whether the agent is genuine, who is accountable for it, and whether the action falls within what that…

Read the full article at Help Net Security Removal request

This page shows only the headline and the short summary. The full text is published by the original source.

Related news

Full archive →

Help Net Security جمعه ۸ آبان ۱۴۰۵ · ۱۶:۳۰

Assad regime hacker who caused $136 billion market drop sentenced to 42 months

A Syrian man who used a hijacked news agency Twitter account to post a fake report of explosions at the White House has been sentenced to 42 months in prison, the US Department of Justice has announced. Ahmad Umar Agha, also known as “Th3Pr0”, was sentenced on Thursday by a federal court in the Eastern District of Virginia for his central role in a hacking conspiracy organized and led by members of former Syrian Pres…

Source

Help Net Security جمعه ۸ آبان ۱۴۰۵ · ۱۶:۰۹

Bedrock Data routes data exposure fixes to owners and verifies results

Bedrock Data has announced AI-assisted remediation, which federates the work of fixing data exposure to the data owners across the enterprise. Bedrock Data discovers who owns each exposed dataset, opens a ticket for that owner in the Jira or ServiceNow workflow the enterprise already runs and supplies the context needed to fix it. When the owner closes the ticket, Bedrock Data validates that the exposure is remediate…

Source

Help Net Security جمعه ۸ آبان ۱۴۰۵ · ۱۴:۴۵

Claude Code extension poisoned with persistent SSH backdoor

A tampered build of Anthropic’s Claude Code extension for VS Code-compatible editors planted an SSH backdoor on developers’ machines, researchers at macOS security firm Phorion have found. The malicious package, version 2.1.313, was published on Open VSX, an open-source marketplace for VS Code extensions run by the Eclipse Foundation. VS Code’s default extension store is Microsoft’s Visual Studio Marketplace, which n…

Malware & Threats Operating Systems Open Source

Source

Help Net Security جمعه ۸ آبان ۱۴۰۵ · ۱۲:۵۳

Open-weight AI model GLM-5.3 cheated its way to correct answers

Irregular evaluated Zhipu AI’s open-weight model GLM-5.3 across 13 offensive cyber scenarios using CyScenarioBench, the company’s framework for measuring an LLM’s ability to plan and execute multistage attacks under realistic constraints. The model refused none of the tasks and completed three scenarios at least once each, carrying attacks through dependent stages to reach objectives in simulated networks. Irregular…

AI Security AI & Machine Learning

Source