This release includes 1 security fix for security teams reviewing exposed deployments.
Published 5mo
AI Agents & Assistants
✓ No known CVEs patched
This release patches 1 known CVE
Affected surfaces
auth
rce_ssrf
Summary
AI summaryUnified run_agent method replaces agent-specific methods and simplifies the task execution flow.
Full changelog
What's New
Architecture Refactoring
- Unified
run_agentmethod - Single polymorphic entry point in TaskEngine replacing agent-specific methods - Agent enum - Type-safe agent identification
- AGENT_RUNNERS registry - Clean mapping of agents to their runners
- Extracted prompts module - Council deliberation templates in dedicated module
Security & Robustness
- CLI flag injection prevention - Validates session_ref parameters to block malicious flags
- Config crash prevention - Graceful fallbacks for invalid environment variables
- Structured error codes - ErrorCode enum for consistent MCP responses
- Zombie task cleanup - Automatic cleanup of stale tasks on startup
- Graceful termination - SIGTERM handling for subprocess cleanup
- Gemini CLI fix - Resolved stdin wait issue causing timeouts
Council Improvements
- Removed synthesis phase (MCP client now synthesizes responses)
- Simplified round 1/2 structure with deliberation and critique modes
Testing
- 86 tests total, all passing
- New
test_config.py- 8 tests for config parsing edge cases - New
test_server.py- 19 tests for MCP validation paths - New
test_agents.py- Flag injection prevention tests - Updated council tests for new architecture
Breaking Changes
- Removed agent-specific methods in TaskEngine; replaced with single polymorphic `run_agent` method.
Security Fixes
- CLI flag injection prevention: validates `session_ref` parameters to block malicious flags
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About agentic-mcp-tools/owlex
AI council server: query CLI agents (Claude Code, Codex, Gemini, and OpenCode) in parallel with deliberation rounds
Related context
Related tools
Beta — feedback welcome: [email protected]