copy

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow ("Voice-of-Customer (VOC) Research" in SKILL.md and Phase 2 in references/landing-page-workflow.md) explicitly instructs the agent to mine and extract verbatim content from public, user-generated sources (reviews on G2/Capterra, competitor reviews, app store reviews, support tickets, sales call transcripts), which the agent would read and incorporate into messaging—exposing it to untrusted third-party content that could carry indirect prompt-injection.