leadoku
Warn
Audited by Snyk on May 1, 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 instructions (SKILL.md "Popular actions" section) include actions like "Get New Connections" that explicitly retrieve LinkedIn connections and responders, meaning the agent will fetch and process user-generated social media/third-party content from external services via Membrane.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata