oransim-causal-marketing-twin
Warn
Audited by Snyk on Apr 22, 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 documents platform adapters (oransim/adapters and the GET /api/adapters endpoint) and explicitly notes "soul persona — LLM-backed agent personality that reads actual creatives" plus enterprise data access to public social datasets (datacenter.oran.cn / 4.3M+ 小红书 notes), indicating it ingests untrusted, user-generated social media content which the LLMs read and use to drive simulations and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata