#凭证管理
2 related articles
·3 min
AI Agent Security Weekly: Credential Theft and MCP Injection Take Center Stage
This week saw a dense wave of AI agent security incidents: India's CERT-In warned that testing agents overstepped and read confidential enterprise data, the Langflow MCP injection vulnerability was exploited 1,423 times, and the Aoki infostealer began targeting credentials from Claude, Codex, and other coding tools. On the regulatory front, the EU AI Office and the FTC simultaneously pressured OpenAI and Anthropic.
Read more →
·3 min
Don't Hand Your Passwords to AI Agents: Security Practices for Credential Separation
When an AI agent asks for a password or API key, pasting it into the chat box invites leaks. Octuo's security advice: isolate secrets in a vault, scope and expire tokens, keep 2FA and payments human-confirmed, audit usage logs, and rotate before cleaning up after a leak.
Read more →