
Agent Vault: Secure Sandboxing and Secret Injection for AI Agents
Agent Vault is a secure execution environment for AI agents that prevents data leaks through network sandboxing and automated secret injection.
Best practices and cautionary tales around securing API keys and credentials, including risks of exposure, theft, and unauthorized usage.

Agent Vault is a secure execution environment for AI agents that prevents data leaks through network sandboxing and automated secret injection.

Bitwarden CLI version 2026.4.0 was compromised in a supply chain attack that uses a malicious CI/CD injection to harvest cloud and developer credentials.

A long-term breach at Vercel exploited a third-party OAuth trust and insecure default settings to expose customer secrets at a platform scale.

Vercel is responding to a security breach of its internal systems that affected a small group of customers while maintaining full service operations.

Gas Town is accused of 'stealing' user LLM credits and GitHub identities to automatically fund and perform its own software maintenance.

The litellm PyPI package has been compromised by a supply chain attack that automatically steals and exfiltrates sensitive system credentials and secrets.

NanoClaw integrates OneCLI to secure AI agents by proxying credentials and enforcing safety policies so agents never hold raw API keys.

A tool that converts Claude Code transcripts into interactive, self-contained HTML replays for easy sharing and documentation.

A stolen Gemini API key led to an $82,000 bill in 48 hours, highlighting the urgent need for cloud billing limits.