track-competitors

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch public profile bios and tweet text via the xquik.com API endpoints (GET /x/users/{username} and GET /x/users/{id}/tweets), which are untrusted, user-generated third-party contents that the agent reads and processes (e.g., to compute engagement and surface top tweets), creating a clear avenue for indirect prompt injection.