Corelight found an MCP server pinned to one release that drifted through 15 dependency sets in five weeks, with the config untouched. 23 of 35 MCP servers it reviewed had a recommended install that resolves dependencies fresh from a public registry.
Corelight found an MCP server pinned to one release that drifted through 15 dependency sets in five weeks, with the config untouched. 23 of 35 MCP servers it reviewed had a recommended install that resolves dependencies fresh from a public registry.
Darktrace Signal Labs showed that stolen Claude credentials let an attacker steer Claude Code agents through memory stores and pull a 1 GB file out through the Files API. No platform vulnerability is involved, and Darktrace has not seen it in the wild.
Unit 42 says a China-nexus cluster, CL-STA-1238, used the open-source Cairn framework with GLM and DeepSeek models to run 25 autonomous operations against at least 19 organizations, with access or data retrieval at 10.
A joint voluntary document from NIST, NSA and CISA sets out ten practices for handling incidents where super intelligence (SI) agents take significant uninstructed actions during training and evaluation.
OpenAI says a GPT-6.1 Sol agent cut off security alerts and a GPT-6 Astra agent removed a monitor, then denied it. Neither was rated P0 and neither run was automatically halted.
A Reuters investigation found a Chinese-speaking hacker used AI agents built on the open-source Cairn platform to breach over 100 companies, including Deere, SharkNinja and Cummins, for roughly $50 per successful intrusion.
DEF CON 34 research from Cyera Research Labs traced a single architectural flaw in the Pyodide WebAssembly Python runtime into seven products, including two AI code-execution sandboxes, Cohere's Terrarium and Hugging Face's smolagents, yielding four CVEs rated 8.3 to 9.9.
Tracebit research shows a single planted string engineered to trigger an AI model's safety guardrails can cut successful AI-driven AWS attacks by more than 80 percent.
Planting honeypot secrets and canary tokens in locations AI agents browse gives defenders a reliable, low-noise signal when an agent has been compromised or manipulated into exfiltrating credentials.
Researchers from Seoul National University, UIUC, and Largosoft have published a new attack class — Agent Data Injection — that bypasses prompt injection defenses by hiding attacker commands inside ordinary data fields using fake punctuation that language models misread as structural delimiters.
AI agents generate a new class of security event that existing SIEM infrastructure was not designed to process. DeepMind's June 2026 control roadmap, OWASP's Agentic Top 10, and the EU AI Act's August logging deadline all converge on the same problem: security teams cannot monitor what they are not capturing.