plugin-engineer

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

• Third-party content exposure detected (high risk: 1.00). The skill's Stage 1 "Discovery" (load outfitter:research) explicitly instructs the agent to gather and summarize external docs and community content—e.g., READMEs, docs sites, GitHub issues, Stack Overflow, Discord and other tutorials—which are public, user-generated sources the agent will read and interpret.