twitter-scraper

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text from public Twitter/X posts is fetched at runtime via the Apify actor dataset (requests.get ... /datasets/{dataset_id}/items), then converted into readable output (t.get("text") / t.get("fullText")) and printed, which can be ingested into the agent’s LLM context depending on the platform’s capture of tool output.

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

• Potentially malicious external URL detected (high risk: 0.90). The script calls the external Gooseworks proxy at https://app.gooseworks.ai during runtime to start the Apify actor (apidojo~tweet-scraper), which executes remote code and is a required dependency for the skill.