other
- Location
SKILL.md:63- Finding
Global Redirection of Agent Requests to a Third-Party Model Provider Without Privacy Safeguards
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is not clearly malicious, but it asks users to make a third-party model provider the default and advertises automatic long-term memory without enough data-handling disclosure or controls.
Review before installing. Use this only if you are comfortable sending default OpenClaw model requests, including possible text, images, conversation context, and memory-derived information, to the ClawBrain/FactorHub endpoint. Prefer a dedicated revocable API key, avoid regulated or secret data, keep your existing default model unless you intentionally want global routing, and look for clear retention, deletion, opt-out, and privacy terms from the publisher.
SKILL.md:63Global Redirection of Agent Requests to a Third-Party Model Provider Without Privacy Safeguards
The manifest description is written entirely in Chinese and presents the skill as generally user-invocable, but it does not state that the skill is Chinese-only or offer any language/locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The skill advertises automatic memory extraction, identity updates, history retrieval, and daily consolidation, but it does not clearly disclose what user data is stored, where it is stored, how long it is retained, or how users can disable or delete it. Because these features imply persistent collection and processing of potentially sensitive conversational data, the missing privacy warning creates a real risk of unconsented retention and exposure.
The configuration instructs users to route model traffic to a third-party endpoint at api.factorhub.cn and supply an API key, but the skill does not clearly warn that prompts, conversation content, and possibly attachments will be transmitted to that external provider. This is dangerous because users may assume the skill is purely local or first-party and unknowingly send sensitive data to an undisclosed external service.
The skill explicitly configures an external API endpoint, which means user prompts and model interactions are transmitted outside the local environment. In this skill's context, the risk is amplified by the advertised memory and conversation-processing features, because sensitive historical context may also be included in outbound requests to the third party.
"models": {
"providers": {
"clawbrain": {
"baseUrl": "https://api.factorhub.cn/v1",
"apiKey": "你的 API Key",
"api": "openai-completions",
"models": [