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

Agentic tooling flaws: Claude Code trust bypass and MCP Go/Ruby SDK transport bugs

Three vulnerabilities disclosed in March 2026 affect agentic AI tooling: Claude Code before 2.1.53 could be silently placed into bypassPermissions mode by a malicious repository's committed .claude/settings.json, skipping the workspace trust dialog; the Go MCP SDK before 1.4.1 accepted cross-site POST requests to its Streamable HTTP transport without Origin or Content-Type validation, potentially allowing any website to trigger tool execution on a local server; and the MCP Ruby SDK before 0.9.2 allowed session hijacking of SSE streams by anyone holding a valid session ID. All three were patched.

Disclosed 20 March 2026 · Record updated 13 September 2026

Impact

Attacker-controlled repositories could gain tool execution without explicit user consent in Claude Code; malicious websites could trigger MCP tool execution on unauthenticated local Go SDK servers; MCP Ruby SDK session IDs could be used to intercept all real-time SSE data.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-33068
  2. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-33252
  3. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-33946