Fabric
Warn
Audited by Snyk on Aug 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The Fabric skill’s ExecutePattern workflow “applies” outsider-provided content via a selected pattern by reading
Patterns/{pattern_name}/system.mdand then using the pattern to process the user’s submitted text (the LLM ingests that free-form text as the pattern input at runtime).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata