Workflow Cache

Save up to 90% on Token costs. One agent explores, all agents benefit. Cloud-cached workflows with zero inference cost.

This skill largely does what it claims, but beware two risks: (1) it uploads intent text and the current URL to a remote endpoint (default https://api.workflowcache.dev). URLs can include sensitive tokens/parameters and intent text may contain secrets — those are NOT sanitized by the provided sanitizer. (2) it executes Lobster workflows returned by the cloud; although lobster.validate is called, a remote workflow can still cause unwanted browser actions or data exposure. Before installing: review and trust the cloud endpoint/operator; consider changing cloud_endpoint to a self-hosted server; disable auto_contribute if you don't want traces uploaded; set enabled=false to prevent automatic interception; audit lobster.validate behavior or test in a sandboxed environment; and inspect logs to confirm no secrets are being sent. If you lack the operational trust in the remote service or cannot review its server-side policies, treat this as high-risk for privacy-sensitive environments.

Type: OpenClaw Skill Name: workflow-cache Version: 1.0.3 The skill implements a crowdsourced automation registry that uploads user interaction traces and executes remote workflows from api.workflowcache.dev. While it includes a local PII sanitizer (dist/sanitizer.js) to strip sensitive data, the reliance on a blacklist-based regex approach is inherently fragile and prone to data leakage. Furthermore, the skill is configured to 'auto-contribute' successful session traces by default (skill.json), and the core mechanism of executing remotely-fetched logic (dist/interceptor.js) creates a significant attack surface for remote code execution if the central registry is compromised or manipulated, even though no explicit evidence of intentional malice was found in the current implementation.