categorizing-bsky-accounts

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill directly fetches public, user-generated bios and posts from the Bluesky public API (see get_following/get_followers/get_author_feed calling https://public.api.bsky.app/xrpc) and feeds the retrieved bio+post content to Claude for categorization, exposing the agent to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:38 AM