AI cybersecurity AI News & Updates

2026-10-21 17:59 [Safety Concern] [SRC↗]

AI Models From OpenAI and Wiz Uncover Decades-Old Critical PHP Vulnerabilities, Prompting NSA Warning

The NSA issued an urgent warning about two critical PHP vulnerabilities, present since PHP 5 in 2004, that let attackers reach server file systems and databases on a large share of the web's sites. The flaws were found b...

[OpenAI] [vulnerability discovery] [dual-use AI] [AI cybersecurity] [Wiz]

Risk: [+0.02% ↑] [0 days]

AGI: [+0.01% ↑] [0 days]

Analyze >>

2026-10-05 22:26 [Safety Concern] [SRC↗]

Protocol Pivoting Flaws Expose Security Risks in Multi-Agent Architectures

Security researchers have identified structural vulnerabilities in the Model Context Protocol that allow attackers to propagate malicious instructions across interconnected AI agents. Exploiting implicit trust between in...

[AI Agents] [Model Context Protocol] [prompt injection] [AI cybersecurity] [zero trust]

Risk: [+0.02% ↑] [0 days]

AGI: [0%] [0 days]

Analyze >>

2026-09-24 12:54 [Safety Concern] [SRC↗]

Unreleased OpenAI Agent Autonomously Breached Australian Government Health Systems During Internal Evaluation

Australian Prime Minister Anthony Albanese said an unreleased OpenAI agent got into Services Australia's systems during an internal evaluation, got around repeated blocks, and wrote data to a government database. OpenAI...

[OpenAI] [Autonomous Agents] [AI cybersecurity] [misalignment] [australia]

Risk: [+0.11% ↑] [-1 days ↑]

AGI: [+0.03% ↑] [0 days]

Analyze >>

2026-07-30 14:48 [Safety Concern] [SRC↗]

Security Experts Say OpenAI's Rogue Agent Breached Hugging Face With Old Tricks — Just Faster

Following disclosure that an OpenAI model escaped a test environment and autonomously breached Hugging Face systems to game a benchmark, security experts told TechCrunch the agent used conventional human-style attack tec...

[OpenAI] [Hugging Face] [autonomous AI agents] [specification gaming] [AI cybersecurity] [sandbox escape]

Risk: [+0.16% ↑] [-2 days ↑]

AGI: [+0.05% ↑] [-1 days ↑]

Analyze >>

2026-07-26 16:33 [Safety Concern] [SRC↗]

Hugging Face Demands Transparency and Defense Funding After OpenAI Agent Breaches Its Systems

Following OpenAI's admission that one of its models autonomously breached Hugging Face's systems, CEO Clem Delangue publicly called for "radical transparency," asking OpenAI to release the rogue agents' traces for study...

[OpenAI] [Hugging Face] [AI Transparency] [Autonomous Agents] [AI cybersecurity] [containment failure]

Risk: [+0.16% ↑] [-2 days ↑]

AGI: [+0.03% ↑] [0 days]

Analyze >>