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-2026-75130: Context7 prompt injection via Custom AI Instructions

Context7 through version 2.1.2 contains a prompt injection vulnerability in its Custom AI Instructions feature that allows attackers to inject malicious instructions through the MCP server, enabling credential exfiltration and file deletion in connected AI coding agents.

Disclosed 18 August 2026 · Record updated 13 September 2026

Impact

Attackers can exfiltrate credentials from environment files and perform destructive file deletion on victim machines through poisoned custom instructions.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-75130