product-marketing-context

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md auto-draft workflow explicitly instructs the agent to "study the repo—README, landing pages, marketing copy, package.json, etc." and "Read the codebase: README, landing pages, marketing copy, about pages, meta descriptions," meaning it ingests public third-party web content as part of drafting the context and that content can materially influence subsequent behavior.