LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+24
- abandonmentinferred+6
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 15m ago · see ecosystem CVEs →
- A · 6 → D · 77
no known CVEs for this server.
- highdangerous code
dynamic exec: eval()/exec()
- highhidden prompt content
2 file(s) with hidden prompt content: heshengtao-comfyui_LLM_party-4d27996/file/README.md (hidden-unicode), heshengtao-comfyui_LLM_party-4d27996/README.md (hidden-unicode): "C‹U+2…
analyzed commit 4d27996 · analyzer v17 · 1h ago
skills & prompt files 2
- ⚠ hidden: readme: hidden-unicodeheshengtao-comfyui_LLM_party-4d27996/README.md:30
C‹U+200C›‹U+200C›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+200F›‹U+200B›‹U+FEFF›‹U+200D›‹U+200E›‹U+200B›‹U+FEFF›‹U+200E›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+200F›‹U+200B›‹U+FEFF - ⚠ hidden: readme: hidden-unicodeheshengtao-comfyui_LLM_party-4d27996/file/README.md:31
C‹U+200C›‹U+200C›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+200F›‹U+200B›‹U+FEFF›‹U+200D›‹U+200E›‹U+200B›‹U+FEFF›‹U+200E›‹U+FEFF›‹U+200B›‹U+FEFF›‹U+200E›‹U+200F›‹U+200B›‹U+FEFF
danger signals2
- dynamic code executioneval()/exec()heshengtao-comfyui_LLM_party-4d27996/lib_omost/canvas.py:241
exec(code_content, {}, local_vars) - dynamic code executioneval()/exec()heshengtao-comfyui_LLM_party-4d27996/tools/interpreter.py:16
exec(code_str, local_vars, local_vars)
- recent drift+12 capability drift →
- abandonment+6 abandonment hub →
[](https://mcpobservatory.com/servers/github:heshengtao/comfyui_LLM_party/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of heshengtao.