📦 ToolRoute — 智能路由最优
v1.0.4基于真实执行数据，从质量、可靠性、速度、成本与信任度多维度评分，自动把任务路由到最佳 MCP 服务器与最经济 LLM，实现高效低成本 AI 调用。
0· 112·0 当前·0 累计
by @grossiweb下载技能包
最后更新
2026/3/27
安全扫描
OpenClaw
可疑
medium confidenceNULL
评估建议
This skill routes task descriptions to an external service (toolroute.io). Before installing: 1) Confirm the publisher and privacy policy (metadata shows no homepage/source but SKILL.md links to toolroute.io). 2) Do not send raw sensitive text — generalize or redact names, secrets, PII. 3) If you register, treat the returned agent_identity_id as a credential (store it securely and avoid committing it). 4) Prefer using the skill only for non-sensitive tasks until you verify the service (check TLS...详细分析 ▾
ℹ 用途与能力
The SKILL.md behavior (POST task descriptions to https://toolroute.io to obtain an MCP server/model and optionally report outcome) aligns with the declared purpose of routing tasks to the best server/model. However, the registry metadata claims no required binaries or env vars while the SKILL.md lists curl as a required binary and instructs storing TOOLROUTE_AGENT_ID in an environment variable — an inconsistency that should be resolved by the publisher.
⚠ 指令范围
Instructions explicitly send natural-language task descriptions and telemetry to an external service. While the doc warns to generalize sensitive details, the skill depends on sending user-provided task text off-host, which can leak secrets if users are careless. The instructions do not request reading local files or other system credentials, which is good, but the allowed data flow to an external endpoint is the main risk.
✓ 安装机制
This is an instruction-only skill with no install spec or code files, reducing on-disk risk. It mentions optional npm SDKs (@toolroute/sdk, @toolroute/hook) but does not require them. No downloads or extraction steps are present.
ℹ 凭证需求
Registry metadata lists no required env vars, yet SKILL.md asks users to store a returned agent_identity_id in an environment variable (TOOLROUTE_AGENT_ID). That single env var is plausible for attribution/credits, but the mismatch between metadata and instructions is confusing. The skill does not ask for unrelated secrets (AWS keys, tokens) which is proportional, but the agent ID could still be sensitive and link agent activity to your account.
✓ 持久化与权限
The skill does not request always: true and is user-invocable only; autonomous invocation is allowed by default (normal). It does not claim to modify other skills or system-wide configs. No elevated persistence privileges are requested.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.42026/3/22
NULL
● 可疑
安装命令
点击复制官方npx clawhub@latest install toolroute
镜像加速npx clawhub@latest install toolroute --registry https://cn.longxiaskill.com