Skip to content

chatgpt-on-wechat

v2.1.2 Security

This release includes 3 security fixes for security teams reviewing exposed deployments.

โœ“ No known CVEs patched
Read the diff โ†’ Tool health โ†’ What is this tool? โ†’
This release patches 3 known CVEs

Topics

ai ai-agent ai-agents chatgpt-on-wechat claude claude-code
+10 more
codex cowagent deepseek harness llm mcp multi-agent openai openclaw skills

Affected surfaces

rce_ssrf auth

Summary

AI summary

Updates ๐Ÿ›  Improvements & Fixes, ๐Ÿค– New Models, and ๐Ÿ”’ Security Hardening across a mixed release.

Full changelog

๐ŸŒ English | ไธญๆ–‡

๐Ÿ’ฌ Web Console Improvements

This release adds several visual management capabilities to the Web Console, so more configuration can be done in the UI without editing files:

  • Scheduled task management: View, edit, enable/disable, and delete any scheduled task directly in the console. The task list is sorted by enabled status first, then by next run time. Thanks @HnBigVolibear (#2892)
  • Knowledge base categories and document management: The knowledge base can now be organized by category, with documents under each category managed in the UI. Thanks @yangziyu-hhh (#2893)
  • Multiple custom model providers: Configure multiple OpenAI-compatible providers and switch the active one with a single click, fully compatible with existing configuration. Thanks @kirs-hi (#2877)
  • Session renaming: Rename sessions manually to tell parallel tasks apart (#2897)
  • Bash streaming output: Long-running Bash commands now stream their progress in real time. Thanks @yangziyu-hhh (#2879)

๐Ÿงฌ Self-Evolution Improvements

Building on the Self-Evolution introduced in the previous release, this version refines it further:

  • Lower trigger thresholds: The default review thresholds are lowered, so everyday collaboration turns into improvements sooner
  • No concurrent reviews: When a single turn runs long, the idle review no longer fires by mistake, avoiding interference with the active conversation
  • Better review summary: Refined the summary prompt to keep summaries concise, raise their information density, and output them in the conversation language

Documentation: Self-Evolution

๐Ÿค– New Models

  • kimi-k2.7-code: Added and set as the default Kimi model, with kimi-k2.7-code-highspeed also available
  • glm-5.2: Added and set as the default GLM model

Documentation: Models Overview

๐Ÿข WeCom Smart-Bot Callback Mode

The WeCom smart-bot channel adds an HTTP callback mode alongside the existing long connection, so deployments that cannot keep a long connection open can still connect reliably:

  • Mode switching: Switch between websocket (long connection) and webhook (callback) via wecom_bot_mode
  • Encrypted transport: Callback mode fully supports URL verification, message decryption, and passive-reply encryption
  • Stability fixes: Fixed reply interruption, premature stream termination, and temporary image file leaks

Thanks @6vision (#2896 #2869)

Documentation: WeCom Smart Bot

๐Ÿ”’ Security Hardening

  • Vision tool SSRF protection: Validates the target address before resolving an image URL, blocking requests to internal, loopback, and cloud server metadata endpoints. Thanks @kirs-hi (#2886)
  • Web fetch SSRF protection: web_fetch validates the target address before fetching and re-validates every redirect hop, preventing redirects from bypassing the check to reach internal addresses. Thanks @christop (#2900)
  • Skill install path traversal protection: Validates the path when installing a skill, preventing a malicious skill name from escaping the skills/ directory through path traversal and writing to an unauthorized location. Thanks @kirs-hi (#2886)

๐Ÿ›  Improvements & Fixes

  • CLI self-restart: Added the cow self-restart command so the agent can restart its own process
  • Windows compatibility: Persist the cow CLI directory to the user PATH; fixed python -c long commands exceeding the cmd.exe length limit; avoid building greenlet from source during install
  • Custom roles: The role plugin supports customization via standalone prompt files under roles/*.json. Thanks @sufan721 (#2891)
  • Stability fixes: Fixed a KeyError on /cancel and an infinite loop in image compression (Thanks @kirs-hi #2888)
  • Install improvements: Updated the startup script and default config; fixed ASR/TTS defaults, the self-evolution flag, and install hangs
  • Vision tool stability: Increased the vision tool timeout and max_tokens
  • Memory distillation: Removed the output length cap in deep-dream distillation to avoid truncating a large MEMORY.md

๐Ÿ“ฆ Upgrade

Source-code deployments can run cow update for a one-click upgrade, or pull the latest code and restart manually. See the Upgrade Guide for details.

Release Date: 2026.06.18 | Full Changelog

Security Fixes

  • Vision tool SSRF protection validates target URLs and blocks internal/loopback/cloud metadata endpoints
  • Web fetch SSRF protection validates each redirect hop to prevent bypass of URL checks
  • Skill install path traversal protection validates installation paths to stop directoryโ€‘escape writes

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

Track chatgpt-on-wechat

Get notified when new releases ship.

Sign up free

About chatgpt-on-wechat

CowAgentๆ˜ฏๅŸบไบŽๅคงๆจกๅž‹็š„่ถ…็บงAIๅŠฉ็†๏ผŒ่ƒฝไธปๅŠจๆ€่€ƒๅ’ŒไปปๅŠก่ง„ๅˆ’ใ€่ฎฟ้—ฎๆ“ไฝœ็ณป็ปŸๅ’Œๅค–้ƒจ่ต„ๆบใ€ๅˆ›้€ ๅ’Œๆ‰ง่กŒSkillsใ€้€š่ฟ‡้•ฟๆœŸ่ฎฐๅฟ†ๅ’Œ็Ÿฅ่ฏ†ๅบ“ไธๆ–ญๆˆ้•ฟ๏ผŒๆฏ”OpenClawๆ›ด่ฝป้‡ๅ’Œไพฟๆทใ€‚ๅŒๆ—ถๆ”ฏๆŒๅพฎไฟกใ€้ฃžไนฆใ€้’‰้’‰ใ€ไผๅพฎใ€QQใ€ๅ…ฌไผ—ๅทใ€็ฝ‘้กต็ญ‰ๆŽฅๅ…ฅ๏ผŒๅฏ้€‰ๆ‹ฉOpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI๏ผŒ่ƒฝๅค„็†ๆ–‡ๆœฌใ€่ฏญ้Ÿณใ€ๅ›พ็‰‡ๅ’Œๆ–‡ไปถ๏ผŒๅฏๅฟซ้€ŸๆญๅปบไธชไบบAIๅŠฉ็†ๅ’Œไผไธšๆ•ฐๅญ—ๅ‘˜ๅทฅใ€‚

All releases โ†’

Beta — feedback welcome: [email protected]