Social Graph Tracking

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

• Third-party content exposure detected (high risk: 0.90). The skill directly calls public ATProtocol endpoints (API_BASE = https://public.api.bsky.app) in references/social.py—get_my_follows, get_my_followers, and get_recent_interactions (app.bsky.feed.getAuthorFeed and app.bsky.feed.getPostThread)—and ingests user-generated handles, display names and post/reply data from the open social network into its processing, exposing the agent to untrusted third-party content that could carry indirect prompt injection.