copycat
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md defines a runtime workflow that invokes subagents to “search” and “read” iOS/Android store listings (seed mode anchors a user-provided product link, then reviews/research are gathered for selected listings), creating an indirect prompt-injection surface through outsider-authored app-store text (e.g., reviews/listing descriptions) that the required workflow ingests after selecting items.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata