openclaw-marketing-skills

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves auditing or analyzing specific URLs provided by the user, which constitutes active fetching of web pages (low risk under the threat model).

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions use git clone to pull skills from an arbitrary personal GitHub repository (LeoYeAI/openclaw-marketing-skills), constituting an unofficial operational dependency.