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-2026-22792: 5ire MCP client HTML injection enables MCP server creation and RCE

Versions of the 5ire cross-platform desktop AI assistant and Model Context Protocol client prior to 0.15.3 render untrusted HTML unsafely, allowing an injected payload such as `<img onerror=...>` to execute arbitrary JavaScript in the renderer. The script can call exposed bridge APIs like window.bridge.mcpServersManager.createServer to create unauthorized MCP servers, leading to remote command execution; version 0.15.3 fixes the issue.

Disclosed 21 January 2026 · Record updated 13 September 2026

Impact

Arbitrary JavaScript execution in the renderer could create unauthorized MCP servers and lead to remote command execution on affected desktop installations.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-22792