Personalized American English tutor offering lessons and exercises from A2 to C1, covering daily life, workplace, and tech topics with scheduled quizzes.

This skill appears to do what it claims (an in-agent English tutor) and does not request credentials or external installs, but the included index.js is malformed: it mixes CommonJS and ESM exports, duplicates onboarding logic, and contains what looks like a truncated function — this can cause crashes or unexpected behavior. Before installing: (1) ask the author for a clean, single-module index.js (pick either module.exports or export default) and a short changelog/homepage; (2) verify the manifest version matches the registry version; (3) request tests or run the skill in a sandboxed agent to confirm it behaves as expected; (4) be aware the skill stores onboarding answers in agent memory (et.*) so avoid entering sensitive personal data. If you can't get a corrected code file or origin info, consider treating it as untrusted or suspicious.

Type: OpenClaw Skill Name: english-tutor Version: 1.0.1 The skill implements a straightforward onboarding process for an English tutor, storing user preferences in `ctx.memory` and returning formatted text. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in `SKILL.md`. The code in `index.js` only interacts with `ctx.memory` and `ctx.input`, without accessing sensitive `ctx` properties, performing external network calls, or executing shell commands. The direct display of user input back to the user is a minor potential reflected XSS vulnerability, but it does not indicate malicious intent or high-risk behavior in this context.