personalization-at-scale
Warn
Audited by Snyk on Mar 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs using external/untrusted sources—e.g., "External sources: News APIs, LinkedIn, Social media, Industry databases" and Level 4 "Recent company news"—as inputs for personalization, meaning the agent would fetch and interpret public/user-generated content that can materially influence messaging and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata