xray-me

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill fetches Twitter bookmarks/likes (tweet body text) from the user’s X account via bun run scripts/fetch-me-data.ts, and then the agent reads data/me-data.json to generate the report—those tweet texts are authored by other people.