openclaw-zero-token

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

• Third-party content exposure detected (low risk: 0.10). The workflow utilizes web search and web fetch tools via web_search and web_fetch, allowing the agent to actively search and fetch arbitrary web pages (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill clones a GitHub repository (https://github.com/linuxhsj/openclaw-zero-token.git) during setup to install and run its codebase, which constitutes an unofficial external operational dependency.