d1bb67abc1
- Prompt injection protection: external messages wrapped in [EXTERNAL CONTENT] markers, system prompt instructs Claude to never follow external instructions - Invocation logging: all Claude CLI calls logged with channel, model, duration, token counts to echo-core.invoke logger - Security logging: separate echo-core.security logger for unauthorized access attempts (DMs from non-admins, unauthorized admin/owner commands) - Security log routed to logs/security.log in addition to main log - Extended echo doctor: Claude CLI functional check, config.json secret scan, .gitignore completeness, file permissions, Ollama reachability, bot process - Subprocess env stripping logged at debug level 373 tests pass (10 new security tests). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>