amazon-keyword-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and scripts explicitly fetch and parse public third-party content—e.g., scripts/research.sh calls Amazon's autocomplete API (completion.{amazon domain}) and SKILL.md instructs using web_search on site:amazon.com and web_fetch on Google Trends—so the agent ingests untrusted, user-driven web content that directly influences analysis and next actions.