autogen
75 issues found
[Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard
5/31/2026
_rstrip_last_assistant_message only strips trailing whitespace from the content — it does not remove the assistant message.
5/30/2026
Safety Report: AI Agent Guardrails Do Not Work — 56-Day Proof (06K Loss)
5/30/2026
Your project scores highest on Safety/Integrity (23.8/30) in an independent trust analysis
5/29/2026
RFC: Cross-agent shared memory store with on-demand capsule recall (agent/group/global scopes)
5/25/2026
docs: use explicit UTF-8 encoding in redirect generation script
5/25/2026
[Feature] FunASR as self-hosted speech-to-text tool for voice agents
5/23/2026
Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec
5/20/2026
Discussion: should AutoGen agents discover tasks from external open markets at runtime?
5/16/2026
SunfishLoop: A public coordination layer for AutoGen agents
5/17/2026
Security: Add OWASP Agent Memory Guard to security docs (memory poisoning protection)
5/13/2026
openai.BadRequestError when using Gemini models for tool calls
5/12/2026
Tool: NEXUS pay-per-call financial data via x402
5/11/2026
Security: OWASP Agent Memory Guard – memory poisoning protection for AutoGen agents
5/10/2026
Proposal: optional Agent Threat Rules security wrapper for autogen-ext
5/9/2026
GroupChat round-robin skips agent when max_round is even
5/9/2026
[Security] Critical: Unauthenticated RCE via WebSocket team_config (CVSS 9.8)
5/7/2026
Mycelium Trails — post-execution accountability receipts for AutoGen agents (notification)
5/5/2026
Suggestion: mcp-swiss-army - All-in-one MCP Server (16 tools, no API keys)
5/5/2026
📝 Integration Proposal: CAJAL — Local Scientific Paper Agent
5/4/2026