peep

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and referenced docs (e.g., references/news.md, references/bookmarks.md, SKILL.md commands) show the tool fetches and ingests user-generated content from X/Twitter (via peep read, search, news, bookmarks, thread, etc.) and also allows posting/replying (peep tweet, peep reply), so untrusted third-party content can be read and materially influence subsequent actions.