Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 7 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

CVE-2026-25533: Sandbox escape in Enclave JavaScript sandbox for AI agent code

Versions of the Enclave (enclave-vm) secure JavaScript sandbox prior to 2.10.1 contain multiple weaknesses — AST sanitization bypass via dynamic property access, incomplete error-object hardening, and Function constructor access via host object references — that allow AI agent code to escape the sandbox. The issue was fixed in version 2.10.1.

Disclosed 6 February 2026 · Record updated 13 September 2026

Impact

Code executed by AI agents inside the sandbox could bypass the sandbox's security layers and reach host objects, undermining safe code execution guarantees.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-25533