moontv-openclaw-skill

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow involves scraping external CMS sources whose content (synopses and titles) is subsequently ingested by an LLM for highlight generation and processed into reports, exposing the agent to untrusted outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions and code snippets referencing unverified external gateway URLs for API queries and configuration, establishing a weak/unknown operational dependency.