competitive-landscape

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 explicitly instructs doing "fresh web research" and to search public third‑party sources (crypto Twitter, GitHub, DefiLlama, app directories) — see SKILL.md step 5 and references/ecosystem-catalog-guide.md (which even falls back to the DefiLlama API and GitHub) — and those live, user-generated sources are read and used to decide competitors, crowdedness, and next actions.