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). The skill explicitly fetches and parses public, user-generated X/Twitter content (see scripts/graphql.ts and scripts/http.ts which call https://x.com and GraphQL endpoints, and scripts/main.ts which accepts x.com/twitter.com URLs) and uses that content to drive parsing, follow-up fetches (referenced tweets), media downloads, and output decisions, so untrusted third‑party content directly influences agent behavior.