amazon-keyword-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow and scripts (SKILL.md and scripts/research.sh / README_CN.md) explicitly fetch and ingest public, user-generated Amazon autocomplete suggestions from https://completion.amazon.com (and also pull Google Trends via trends.google.com and general web_search results) and then parse and act on that data to drive analysis and scoring, exposing the agent to untrusted third-party content that could contain injected instructions.