twitter-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly lists and demonstrates apps that fetch public, user-generated Twitter/X content (e.g., x/post-get, x/user-get shown in "Available Apps" and Examples), which the agent would read and could influence automated actions like likes/retweets/follows/DMs, exposing it to untrusted third-party instructions.