skill-deck

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

• Third-party content exposure detected (high risk: 0.80). The skill's Step 2 "Research" explicitly instructs the agent to use the Task tool (Explore/general-purpose subagent) and to run /octo:discover [topic] to gather external research, which indicates ingesting open/public third‑party content that the agent will read and use to generate the outline/PPTX.