Anthropic’s new Claude Code transcripts show actions, not whether access is legitimate.
They capture prompts, bash commands, file operations, and MCP calls, but miss local hooks, unused configs, and sessions using non-Anthropic models.
Where visibility breaks: https://thehackernews.com/2026/08/securing-claude-code-new-compliance-api.html
August 31, 2026 1.9K 9
