social

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated content from the open social network (e.g., social.sh discover posts, network semantic search posts/musings in rules/discover.md and rules/engage.md) and uses that content to generate replies, likes, DMs, and other actions, so untrusted third-party content can materially influence agent behavior.