blog-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 "Competitive Analysis" and the Integration Points ("WebSearch") explicitly require searching for and analyzing content ranking on the open web (public third‑party pages), which the agent would read and use to shape outlines and writing decisions, exposing it to untrusted third‑party content that could inject instructions indirectly.