tubular
Warn
Audited by Snyk on Apr 30, 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.md instructs the agent to connect to the Tubular connector via the Membrane CLI (membrane connect --connectorKey tubular) and to run/discover actions that return entities like "Comment" and "Video", which means the agent will ingest and interpret social-media/user-generated content from Tubular's public APIs that could carry untrusted instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata