hivo-salon

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to read and act on user-generated salon messages (e.g., via "hivo salon message list" and "hivo salon message get" and the --mention-me flow), which are untrusted third-party content that could contain instructions influencing agent actions.