fetch-tweet

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses arbitrary public X/Twitter content via the FxEmbed API (https://api.fxtwitter.com/ as described in SKILL.md and scripts/fetch_tweet.py), ingesting untrusted user-generated tweet text and metadata which the agent reads, translates, and acts upon, enabling indirect prompt-injection risks.