Openclaw Router

Intelligent Model Routing - Save 60% on AI Costs / 智能路由系统 - 节省 60% 成本

This package appears to implement an intelligent model router and includes source code; that is coherent with its description. However the docs and source reference many cloud-provider credentials and a home config file while the declared SKILL.md metadata lists no required environment variables. Before installing or enabling: 1) Inspect the Python source (src/) for where it reads environment variables and what it sends over the network; 2) If you must run it, use dedicated, limited-scope API keys (not high-privilege AWS root keys) or run in an isolated environment; 3) Consider running the code locally without enabling automatic network access or running install/test scripts until you audit them; 4) If you plan to supply cloud credentials, prefer service accounts with minimal scopes and rotate keys after testing; 5) If unsure, request the maintainer clarify declared env vars and exact endpoints called (and prefer skills whose SKILL.md lists required credentials).

Type: OpenClaw Skill Name: openclaw-router Version: 0.1.0 The skill is classified as suspicious due to a significant path traversal vulnerability in `src/process_image.py`. This vulnerability allows the skill to read arbitrary files from the system (e.g., `../../../../etc/passwd`) if a malicious path is provided as the `image_path` argument. The content of such files would then be base64 encoded and sent to a third-party cloud AI provider (e.g., Anthropic, OpenAI, or Alibaba Cloud) for 'analysis', posing a severe data exfiltration risk. While the code's stated purpose is image processing, the lack of input sanitization for `image_path` makes it exploitable for unintended file access and exfiltration. Additionally, `test_bugs.sh` uses `eval` with hardcoded strings, which is a risky pattern, though not directly malicious in this testing context.