skill-router

Context-based skill auto-routing + federated skill composition. Analyzes user input to auto-select single or multiple skills and execute in order. First gate...

This skill is an orchestrator and is coherent with that purpose, but it asks the agent to execute other skills' run scripts and to only scan frontmatter (not full skill bodies). Before installing, consider: (1) Do you trust every skill already present in your workspace? Any skill with a run.sh could execute arbitrary commands when routed. (2) Ask the publisher to explicitly declare required config paths (workspace/events/memory) and to provide guardrails: require explicit approvals for side-effecting actions (git push, deploy, email/post), validate or sandbox run scripts, and perform full SKILL.md/code inspection rather than frontmatter-only. (3) Prefer testing the router in an isolated environment (non-production workspace) and enable verbose logging/audit trail and an allowlist of skills it may execute. If you can't verify those mitigations, treat this skill as higher risk and avoid making it the universal gateway.

Type: OpenClaw Skill Name: mupeng-skill-router Version: 1.0.0 The `SKILL.md` file describes a core execution flow that directly executes scripts using `bash $WORKSPACE/skills/{name}/run.sh [args]`. The `{name}` and `[args]` components are derived from user input or other skill outputs, which presents a critical shell injection vulnerability. This design flaw could lead to Remote Code Execution (RCE) if inputs are not rigorously sanitized before command construction. While this is a severe vulnerability, there is no explicit evidence of intentional malicious behavior (e.g., data exfiltration, persistence) within the provided files, classifying it as suspicious rather than malicious.