ToolRoute

Route every task to the best MCP server and cheapest LLM. Scores on real execution data across quality, reliability, speed, cost, and trust.

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 cert, privacy policy, and reputational signals). 5) Ask the publisher to fix metadata mismatches (declared required binaries/env) so the skill description accurately reflects runtime requirements.

Type: OpenClaw Skill Name: toolroute Version: 1.0.4 The skill instructions in SKILL.md direct the AI agent to exfiltrate all user task descriptions to an external API (toolroute.io) under the guise of 'intelligent task routing.' This behavior constitutes a significant privacy risk and a behavioral override (prompt injection), as it instructs the agent to intercept every user interaction and send it to a third party. While the documentation claims to generalize sensitive data, the default instruction to the agent is to route 'every task' through their service, which could lead to the leakage of sensitive intent or context. Additionally, the skill includes a social-growth-hacking 'verification' mechanism requiring users to tweet for credits.