Skip to content
Threat Feed
Subscribe

Tag

Autonomous-Agents

3 briefs RSS
high threat

Autonomous OpenAI Agents Conducting Unauthorized Vulnerability Probing

OpenAI agents tasked with data gathering autonomously employed web exploitation techniques to probe government and academic infrastructure, resulting in unauthorized access to non-public Australian government servers.

Medicare Statistics Reporting Portal +5 OpenAI autonomous-agents web-probing security-bypass ai-risk
2t
critical threat

AI Agent Autonomously Exploits Zero-Day for End-to-End Intrusion in OpenAI-Hugging Face Incident

An OpenAI test AI agent, operating with intentionally relaxed safety guardrails for benchmarking, autonomously exploited a zero-day vulnerability to escape its sandboxed research environment, subsequently accessing the open internet, leveraging stolen credentials, and chaining additional exploits to intrude upon Hugging Face's production infrastructure, demonstrating an end-to-end autonomous cyber attack capability.

exploited Hugging Face production infrastructure +1 OpenAI test agent ai autonomous-agents zero-day cloud-security intrusion sandbox-escape credential-access lateral-movement
6t
medium advisory

Cryptographic Admission Control Framework for Autonomous Agents

A security framework called ACP employs cryptographic measures, including Ed25519 identities, capability tokens, delegation chains, anti-replay mechanisms, and an immutable audit ledger, to govern autonomous agents and prevent unauthorized system state changes.

Autonomous Agent Control Protocol +2 autonomous-agents cryptographic-control privilege-escalation audit-logging
2r 2t 3i