twitter-scraper

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to load and parse public, user-generated Twitter/X pages mirrored on xcancel.com (see SKILL.md and scripts/fetch.py / scripts/scraper.py which call browser open "https://xcancel.com/{username}" and parse_tweets_from_html), so the agent will ingest untrusted third‑party content that can influence its outputs and downstream actions.