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

Langroid SQLChatAgent prompt injection enables RCE on database host (CVE-2026-25879)

Prior to version 0.63.0, Langroid's SQLChatAgent executed LLM-generated SQL that could be steered by direct or indirect prompt injection; with a privileged database role, an attacker could invoke dialect-specific primitives such as COPY ... FROM PROGRAM to achieve remote code execution on the database host. Fixed in v0.63.0 by defaulting to a SELECT-only parsed statement allowlist with a dangerous-pattern blocklist.

Disclosed 1 June 2026 · Record updated 13 September 2026

Impact

Attackers able to influence the agent's input, including via data returned to the LLM, could coerce execution of dangerous SQL primitives leading to remote code execution on the database host.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-25879