landing-page-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Step 1: "Repository Analysis") explicitly reads and analyzes README.md, docs/, CHANGELOG.md and assets from arbitrary repositories (e.g., GitHub) — public, user-generated content that the agent ingests to build the landing, populate the search index, and generate links/CTAs, so third‑party repo content could indirectly inject instructions that affect actions.