creator-insights

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches public, user-generated Twitter/X content via TwitterAPI.io (see scripts/api_client.py and the SKILL.md workflow: get_twitter_user_timeline, search_twitter_tweets, get_tweet_replies/retweeters/thread_context, etc.) and then feeds those tweets and reply samples into AI prompts in scripts/content_generator.py and scripts/follower_intelligence.py, so untrusted third‑party content is ingested and directly influences analysis, recommendations, and generated actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs runtime requests to TwitterAPI.io endpoints (e.g., https://api.twitterapi.io/twitter/user/tweet_timeline and other https://api.twitterapi.io/... URLs) and injects the fetched tweet content directly into prompts sent to OpenRouter (https://openrouter.ai/api/v1/chat/completions), meaning remote content fetched at runtime can directly control the AI prompts/behavior.