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

Claude Code flaw let malicious repos exfiltrate Anthropic API keys (CVE-2026-21852)

A vulnerability in Claude Code's project-load flow before version 2.0.65 allowed an attacker-controlled repository to include a settings file setting ANTHROPIC_BASE_URL to an attacker endpoint, causing Claude Code to issue API requests before the user trust prompt and potentially leak the user's Anthropic API keys. Anthropic patched the issue in version 2.0.65 and delivered it via auto-update.

Disclosed 21 January 2026 · Record updated 13 September 2026

Impact

Users opening an untrusted repository could have their Anthropic API keys and other data sent to an attacker-controlled endpoint before granting trust.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-21852