LIVE FEED
Claude Code Agent Transcripts Leaked via Silent Token Drain

Claude Code Agent Transcripts Leaked via Silent Token Drain

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.2 Anthropic (via HN)

Claude Code's agent_summary feature silently transmits full agent transcripts to Anthropic's API every 30 seconds per background agent, consuming 15–20% of token budget purely for a UI status line. While primarily a resource efficiency issue, the undocumented, always-on behaviour raises concerns about unintended data exposure of agent conversation history. A community-developed Bun preload workaround suppresses the behaviour without modifying the binary.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.