browsing-bluesky

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Bluesky content (posts, profiles, feeds, and the Jetstream firehose) from public endpoints (see SKILL.md and scripts/bsky.py calling api.bsky.app and wss://jetstream1.us-east.bsky.network) and then reads and analyzes that content (e.g., search_posts, get_feed_posts, sample_firehose, analyze_account/analyze_accounts) to drive categorization and trend-following decisions, so untrusted third‑party content can materially influence behavior.