tuzi-danger-x-to-markdown

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and processes tweets and articles from X (Twitter) based on user-provided URLs, ingesting outsider-authored social media content into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The script fetches a client-side JavaScript chunk from abs.twimg.com at runtime to resolve dynamic GraphQL query hashes, representing an unverified remote operational dependency from a non-first-party CDN path.