Cross-agent tool-call risk scoring with allow, ask, and deny outcomes.
Read Chinese translation
对不同 Agent 的工具调用进行风险评分，输出允许、询问或拒绝的结果。
Community experiments and integrations. Directory reviews are not safety certifications; model judgments do not replace host permission checks.
Related use cases
Directory and research sources
Provenance is retained from the previous edition. This edition did not install or re-audit the project.
cobanov/awesome-jev →