github not analyzable

modelscope/MCPBench

The evaluation benchmark on MCP servers

Drift inferred · capture-to-capture

HIGH 2026-06-14 code analysis flagged dynamic code execution in modelscope/MCPBench

capabilities 0 tools

transport — counts 0 tools · 0 res · 0 prompts permission surface via code analysis

No tools enumerated yet for this server.

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed analyzer v19 · 5h ago

dynamic code executionpickle.loads()modelscope-MCPBench-5f39744/langProBe/synced_mcp_client.py:59func_name, args, kwargs = pickle.loads(request)
suspicious endpoint20.102.90.50modelscope-MCPBench-5f39744/langProBe/dspy_program.py:417rm=dspy.ColBERTv2(url="http://20.102.90.50:2017/wiki17_abstracts"),

code evidence vHEAD · github-tarball

evidence-backed findings quoted directly from the published source artifact — not inferred

last analysis: fetch-failed · showing evidence from the last successful analysis (3d ago)

fs modelscope-MCPBench-5f39744/langProBe/GAIA/data/GAIA.py :71 with open(root_file, "r", encoding="utf-8") as f:
fs modelscope-MCPBench-5f39744/langProBe/GAIA/data/statics.py :30 with open(file_path, 'r', encoding='utf-8') as f:
fs modelscope-MCPBench-5f39744/langProBe/analysis.py :1 import pathlib
fs modelscope-MCPBench-5f39744/langProBe/config_utils.py :6 with open(file_path, 'r') as file:
fs modelscope-MCPBench-5f39744/langProBe/evaluation.py :4 import pathlib
fs modelscope-MCPBench-5f39744/langProBe/evaluation_utils.py :223 os.remove(log_path)