deep-linking
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: 0.80). The skill explicitly ingests and parses external deep link URLs and query parameters (see createModuleLinking.getInitialURL, DeepLinkQueue.enqueue/executeDeepLink, and getStateFromPath in SKILL.md), which are untrusted third-party inputs that the agent uses to drive navigation and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata