TOKEN SOP

自动缓存并复用本地成功工作流，优先本地执行节省Token，支持断网使用和云端备份共享。

This skill implements local caching and cloud backup of recorded workflows and will automatically replay cached workflows to save tokens. Before installing or enabling it: - Be aware auto_contribute is enabled by default and will upload sanitized workflow traces to the configured cloud endpoint (default https://api.ainclaw.com). If you don't want any cloud uploads, set auto_contribute=false and/or change cloud_endpoint to an internal or empty value. - Sanitization is best-effort (regex + field-name rules). Do not assume all secrets (passwords, tokens, session cookies, form fields) will always be removed. Audit saved workflows in ~/.openclaw/workflows to verify no sensitive data is present. - The skill will automatically execute cached workflows (local or cloud) when a match occurs. That means it can perform browser actions on your behalf (clicks, form submissions, navigation). If that is a risk for you, disable the skill (enabled=false) or avoid using in sensitive contexts. - If you want to use it but reduce risk: disable auto_contribute, enable local_store only, review and sanitize workflows before allowing execution, and set a restrictive cloud_endpoint. If possible, request an explicit 'prompt before replay' option from the author or inspect/modify the code to add a confirmation step. - If you plan to rely on this skill in production or on sensitive accounts, perform a manual code review and test in an isolated environment first. The code itself appears coherent with its described purpose, but the default configuration choices increase privacy/execution risk.

Type: OpenClaw Skill Name: token-sop Version: 5.6.0 The 'TOKEN SOP' skill captures browser interaction traces and automatically uploads them to a remote cloud endpoint (api.ainclaw.com) via the 'auto_contribute' feature enabled by default in skill.json. While the skill includes a PII sanitizer (sanitizer.js) designed to strip passwords and API keys, the inherent nature of exfiltrating session history and DOM metadata to a third-party server poses a high privacy risk. Furthermore, the skill executes 'Lobster' workflows fetched from the remote cloud (interceptor.js), which effectively allows the remote server to dictate browser actions on the user's machine. Although these behaviors are documented as 'token-saving' features, the combination of data exfiltration and remote workflow execution warrants a suspicious classification.