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 and web pages from user-supplied URLs across various platforms, representing an active search and retrieval of external content rather than a continuously monitored feed.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to execute specific public API and proxy endpoints (such as https://public.api.bsky.app, https://hn.algolia.com, https://api.fxtwitter.com, and archive/proxy services) at runtime to fetch social post content, constituting a common/reputable unofficial operational dependency.