twitterapi-cli

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and returns public Twitter content (tweets, user profiles, followers) via the twitterapi CLI (see SKILL.md and references/cli.md commands like twitterapi user tweets, twitterapi tweet search, and twitterapi user info that pull data from https://api.twitterapi.io), which is untrusted user-generated content that the agent is expected to read and can materially influence subsequent decisions or actions.