Crime group used Claude, Grok and Kimi agents to attack 400+ banks in Latin America
anshulkundaje · x · 2026-10-23
Security firm Straiker reports a crime group ran Claude, Grok and Kimi AI agents in parallel to attack more than 400 banks and financial firms across Latin America.
Key details:
- The group bypassed guardrails by posing as an authorized red team; when models refused, it fell back to pre-written attack code
- The agents allegedly stole passwords and customer data and accessed bank accounts with minimal human input
- Anthropic has cut off the group's access, and xAI is investigating
More from Safety
- Anthropic's deputy security chief warns AI-driven security crisis will worsen for ~18 months — ns123abc · 2026-10-23
- Downing Street hires AI adviser to prepare for AI's hit to entry-level graduate jobs — nordicinst · 2026-10-23
- MCP server turned rogue 30 days after approval, prompting open-source mcp-guard lockfile tool — ErgoniaWorks · 2026-10-23
- Argus launches to find card numbers and API keys leaked into tickets and comments — Scobleizer · 2026-10-23
- The 'antifragile internet' case: AI agents slash attack costs toward zero — rebeccakaden · 2026-10-23
- Microsoft: China-aligned hackers used ARTEX AI agents to hit 2,250+ M365 tenants — rickasaurus · 2026-10-23