x-founder-operations

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

• Third-party content exposure detected (high risk: 0.90). The skill's automated "Morning Scan" and scheduled tasks (see SKILL.md and references/cron-schedule.md) explicitly fetch and scan public X/Twitter content—mentions, core-circle posts, trending topics and competitor timelines (x-timeline → Get tweet list)—which are untrusted user-generated sources that the agent is required to read and use to decide replies, posting recommendations, and engagement actions, so third-party content could materially influence tool use.