claw-me-maybe

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to fetch and search user-generated messages via the Beeper Desktop API (e.g., "Search Messages Across All Beeper Networks", "List Messages in a Chat" and related /v1/messages endpoints), which ingests untrusted third-party chat content from social networks and can directly influence the agent's summaries, actions, and message-sending behavior.