twitter-reader

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches public, user-generated content directly from Twitter/X via opencli (see SKILL.md Step 3 and references/commands.md) and explicitly instructs the agent to read, summarize, and act on tweet content (e.g., market sentiment), so untrusted third‑party content could influence agent behavior.