cold-outreach

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Writing cold emails that work" section explicitly instructs using public third-party content (e.g., "referencing something specific
• a LinkedIn post, a job listing, a company announcement, a technology choice visible on their website") as part of the personalization workflow, so the agent is expected to fetch and interpret untrusted user-generated/public website content that can change subsequent actions.