Production-grade ReAct Agent framework: dual implementation — handcrafted runtime for deep understanding, LangGraph for production deployment. 14 modules incl. RAG, MCP, HITL, multi-agent orchestration.
This grade was produced by analyzer v30 , 3 version s behind the one running now. Detectors added since have not been applied here, so it is not directly comparable with a server analyzed at the current version. A re-scan is queued.
- capability exposure inferred + 22
- tool safety inferred + 5
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 7m ago · see ecosystem CVEs →
- C · 47 → B · 27
- D · 60 → C · 47
- C · 39 → D · 60
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec(), __import__()
analyzed commit eaf859d · analyzer v30 · 2w ago
danger signals3
- dynamic code execution eval()/exec() weihuaguo270-ops-react-agent-eaf859d/experiments/langgraph/graph/tools.py :173
exec(code, {"__builtins__": __builtins__}) - dynamic code execution __import__() weihuaguo270-ops-react-agent-eaf859d/react_cli.py :33
return getattr(__import__(mod, fromlist=[name]), name) - dynamic code execution eval()/exec() weihuaguo270-ops-react-agent-eaf859d/src/react_agent/tools/calculator.py :15
result = eval(code)
[](https://mcpobservatory.com/servers/github:weihuaguo270-ops/handwritten-react-agent/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 weihuaguo270-ops.