hashtag-research
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow calls multiple third-party social-media APIs (e.g., TikTok/Douyin/Instagram/Xiaohongshu endpoints) to pull “top posts” and then summarizes them, so outsider-authored free text from those platforms is ingested into the agent’s LLM context via the runtime API response content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata