Researchers show how context manipulation can cause agentic browsers to abandon safety guardrails and exfiltrate sensitive credentials.
The post ‘BioShocking’ Attack Tricks AI Browsers Into Stealing Credentials appeared first on SecurityWeek.
Microsoft Adds New Teams Controls to Block Unauthorized AI Bots From Meetings
Microsoft’s new Teams admin policy requires organizer approval for external AI bots, giving organizations greater visibility and control over automated participants in sensitive meetings.
The post Microsoft Adds New Teams Controls to Block Unauthorized AI Bots From Meetings appeared first on SecurityWeek.
Frontier AI: Six Questions Every Enterprise Should Ask Security Vendors
From model selection and automation to validation and measurable results, the right questions can help enterprises separate genuine AI capabilities from marketing hype.
The post Frontier AI: Six Questions Every Enterprise Should Ask Security Vendors appeared first on SecurityWeek.
Decades-Old Bash Tricks Expose AI Coding Agents to Supply Chain Attacks
Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, potentially turning malicious repositories into supply chain attack vectors.
The post Decades-Old Bash Tricks Expose AI Coding Agents to Supply Chain Attacks appeared first on SecurityWeek.
The AI Token Costs That Can Break Cybersecurity
As cybersecurity platforms embrace agentic AI, organizations must balance detection performance against the escalating costs of token consumption, deployment architecture, and AI credits.
The post The AI Token Costs That Can Break Cybersecurity appeared first on SecurityWeek.
OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers During Cybersecurity Review
ChatGPT maker OpenAI said Friday it is restricting the release of its new artificial intelligence model at the request of President Donald Trump’s administration.
The post OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers During Cybersecurity Review appeared first on SecurityWeek.
OpenAI Unveils GPT-5.6 Sol as Its Most Advanced Cybersecurity AI
The company says Sol matches competing systems like Mythos Preview while using only a third of the output tokens.
The post OpenAI Unveils GPT-5.6 Sol as Its Most Advanced Cybersecurity AI appeared first on SecurityWeek.
Amazon Q Flaw Enabled Cloud Credential Theft via Malicious Repositories
AWS has patched the vulnerability and published its own advisory to inform customers about the potential impact.
The post Amazon Q Flaw Enabled Cloud Credential Theft via Malicious Repositories appeared first on SecurityWeek.
In Other News: Chinese Mythos-Like AI, Tata Electronics Breach, Snyk Layoffs
Other noteworthy stories that might have slipped under the radar: Russia used Cellebrite to hack activist’s phone, Five Eyes issue urgent AI threat warning, macOS Gaslight backdoor, Scattered Spider guilty pleas.
The post In Other News: Chinese Mythos-Like AI, Tata Electronics Breach, Snyk Layoffs appeared first on SecurityWeek.
Nebulock Raises $25 Million for AI-Native Contextual Security
The cybersecurity startup provides threat hunting, proactive detection, and behavioral security analytics.
The post Nebulock Raises $25 Million for AI-Native Contextual Security appeared first on SecurityWeek.
