pm-competitor-deconstructor

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow and references (SKILL.md and references/data-sources.md) explicitly direct the agent to collect and analyze public third‑party content—e.g., competitor websites, App Store/G2 reviews, SimilarWeb, Product Hunt, Twitter/X and other social media/community posts—so the agent will ingest untrusted/user‑generated web content that can materially influence its analysis and recommendations.