pinterest-search
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill’s required workflow runs a runtime Pinterest “collect” by keyword and then normalizes returned items including the outsider-authored
title/page text from Pinterest into the agent’s LLM context, creating an indirect prompt-injection path from public web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata