baoyu-danger-x-to-markdown

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and converts public X/Twitter content from user-provided x.com or twitter.com URLs (tweets, threads, and articles), which are untrusted, user-generated third-party content that the agent reads and could therefore carry indirect prompt-injection instructions.