market-researcher

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

• Third-party content exposure detected (high risk: 0.90). This skill's "Competitive Intelligence Gathering" workflow explicitly instructs the agent to use public/untrusted sources—company websites, app store reviews, social media, Crunchbase, LinkedIn—which the agent would read and interpret to inform competitive analysis and decisions, exposing it to indirect prompt-injection from third-party content.