Undeclared Tool Scope
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a simple model recommendation helper with minor disclosure and usability issues, but no evidence of malicious behavior.
Install only if you are comfortable with a Chinese-language model routing helper. Before following its configuration example, back up your OpenClaw config and validate the JSON; also note that the Python module will read /home/skyswind/.openclaw/openclaw.json if that file exists.
Without declared permissions the skill's intent is opaque and cannot be validated.
Most user-facing instructions and descriptions in the skill are written exclusively in Chinese, and the file does not indicate that Chinese is optional or required for a region-specific purpose. This can violate language/locale policy when a skill effectively forces a specific language without user opt-in.
The module docstring and later user-facing strings are written only in Chinese, indicating the skill is designed to operate in a single language. The policy requires avoiding forced language or locale constraints unless the skill offers user opt-in or clearly documents a justified region-specific limitation, which this file does not do.
The manifest promises model selection based on task type, content length, and quality, but the code also consults local agent configuration for model defaults. This hidden behavior creates a trust-boundary mismatch: consumers may invoke the skill expecting pure routing logic, while it also inspects local state, which can expose configuration details and produce non-obvious behavior.
The skill reads a user-specific OpenClaw configuration file and exposes get_agent_model, which reveals per-agent configured model choices unrelated to the manifest’s stated routing function. In a skill context, unnecessary access to local user configuration expands the data-access surface and can leak environment-specific information to other components or prompts that invoke this helper.
The explanatory strings returned to users, such as model descriptions and task-fit labels, are all emitted in Chinese. Because the file does not offer alternative locales or an explicit opt-in, it violates the language-choice policy for natural-language behavior.
The command-line help text shown to users is entirely in Chinese, and there is no option to select another language. This creates a natural-language policy issue because the skill enforces a specific language for user interaction without documented opt-in or locale justification.
The documentation instructs users to directly edit a live OpenClaw configuration file under the user's home directory without cautionary guidance. This can lead to accidental service misconfiguration, broken agent routing, or loss of a known-good setup, especially if users overwrite production settings without backup.