shortcut
Warn
Audited by Snyk on Apr 27, 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.md explicitly instructs the agent to send requests to Apideck's proxy endpoint (https://unify.apideck.com/proxy) which forwards and returns Shortcut's native API responses (see https://developer.shortcut.com/api/rest/v3), meaning the agent will fetch and read untrusted, user-generated Shortcut content as part of its workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata