hardware-saas-gtm

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

• Third-party content exposure detected (high risk: 0.72). Outsider free text is ingested via runtime comments on public platforms (e.g., the Product Hunt commenter quote and other backer/comment text), which the skill’s workflow explicitly instructs to “monitor comments, respond to every question” during the Kickstarter launch window—those comment bodies are outsider-authored prose fed into the agent/LLM context.