x-twitter-scraper

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow ingests outsider-authored free text by searching/fetching public X/Twitter posts and related profile/monitor content (e.g., via keyword/account/time-range searches, timelines, and monitors), so attacker-published poison could be read without any prior selection beyond the user’s search/monitor inputs.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs installing and running remote code via the command "npx skills@1.5.3 add Xquik-dev/x-twitter-scraper", which fetches and executes external package code that the skill would rely on at setup/runtime.