amazon-research
Warn
Audited by Snyk on May 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires collecting Amazon data (URLs, ASINs, reviews, bestseller pages) — e.g., instructing to put category/search URLs in templates/junglee-amazon-crawler-search.json and to "collect" reviews/ listings — and the shared scripts (collection_actor_run.mjs + network_runtime.mjs and hosted collection bridge) perform HTTP requests to ingest public Amazon pages and user-generated reviews which the agent reads and uses to drive analysis and downstream actions, so untrusted third‑party content can influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata