founders-playbook

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

• Third-party content exposure detected (high risk: 0.70). The skill's Idea Stage explicitly instructs building models "from public data" and to "synthesize competitor reviews" (references/idea-stage.md), and the SKILL.md discussion of Claude Cowork connectors/connected data sources indicates the agent is expected to ingest and act on public/user-generated web content, which could carry untrusted instructions influencing decisions.