multi-canister
Warn
Audited by Snyk on Nov 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow is developer-facing design and deployment guidance, and its only outsider-writable data is the user-submitted posts in the app's own
content_service, which the agent reads only when it actively runs thegetPostsandgetPostsWithAuthorverification calls (low, not medium, since the agent must fetch it and nothing forces delivery into a feed).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata