deploy-openclaw-bot-for-me

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to fetch and follow a public GitHub Pages URL (https://vinta.github.io/dear-ai/deploy-openclaw-bot-for-me.md), so it will ingest untrusted third-party content that could contain indirect prompt injections.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). Because the skill explicitly instructs fetching and following runtime instructions from https://vinta.github.io/dear-ai/deploy-openclaw-bot-for-me.md, that external content directly controls the agent's instructions and is a required dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt directs the agent to fetch and follow a deployment guide for installing a bot on a Vultr server, which very likely requires installing packages, editing system/service configuration, and running privileged commands (e.g., sudo/systemd/SSH changes), so it pushes the agent toward modifying machine state and escalating privileges.