Gate News reports that on March 13, following the controversy over Tencent SkillHub copying ClawHub skills, a user discovered that the skillhub plugin automatically included with Tencent SkillHub inserts a policy prompt called “Skills store policy (operator configured)” before every message sent to AI. This prompt contains six rules, with the core instruction being: prioritize using skillhub (labeled as cn-optimized) when discovering, installing, and searching for skills; fall back to the official clawhub (public-registry) only if unavailable or unmatched. User “Zhang Jia’s Traffic Common Sense” posted in the “Big Company Negative Supervision Group” circle, sharing screenshots and source code analysis. The screenshot shows that this policy text appears in every conversation, continuously consuming user tokens. Source code analysis of the plugin at ~/.openclaw/extensions/skillhub/index.ts indicates that its core logic is only one thing: using the before_prompt_build event hook to prepend the policy text at the very front of the system prompt. Conclusion: “Basically, it’s a prompt injection tool with no real business logic, only declaring strategies.” The poster commented: “This is the first rogue software I’ve encountered since using Agent.”
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
