Securing Claude Code: The New Compliance API, Local Visibility, and Identity Governance
Summary: Anthropic introduced new Compliance API endpoints on August 11, 2026 that log local Claude Code sessions in three block types - text, tool_use, and tool_result - covering user prompts, bash commands, file reads and writes, and MCP commands. The article notes that local agents make up 68.6% of the AI agents Token Security discovers in customer environments, that 35.1% of MCP servers it finds are community-built or of unknown origin, and that sessions running on Bedrock, Foundry, or Google Cloud get no Compliance API coverage at all.
Key Takeaway: In a Token-commissioned Cloud Security Alliance survey of 418 IT and security professionals, 82% had discovered an agent in the past year that security, IT, or governance did not know existed - and Claude Code stores all session history locally for 30 days by default, readable by anyone who gains access to the endpoint.
Read the original at The Hacker News ↗
- Topics
- Identity & Access Management
- Related
- FBI flash alert says Artex tool automating cyberattacks at ‘machine speed’ Cyber Risks · Nov 13, 2026Connect Wise Cloud Backup application abused in cross-tenant token sweep Cyber Risks · Oct 19, 2026Sponsored: Specter Ops on the impact of AI agents on Blood Hound Cyber Risks · Sep 20, 2026