social-fetch

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

• Third-party content exposure detected (low risk: 0.10). The agent skill fetches social media posts via URLs provided by the user, which falls under actively fetching specific outsider-authored content (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions to fetch external code and content from multiple third-party APIs and services (such as ScrapeCreators, Apify, and various Nitter instances) at runtime, classifying these third-party web services as common unofficial or weak/unknown external operational dependencies.