chinese-app-benchmark
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Phase 2 "Research Each Competitor" explicitly requires using web_search and image_search to fetch app store screenshots, product analysis articles, and competitor pages (public websites/social media) and instructs the agent to read and act on those findings to drive design and code changes, which exposes it to untrusted third-party content (SKILL.md, Phase 2B).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata