ff15-workspace-operation-customization
Warn
Audited by Snyk on Jul 29, 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 validator/runtime workflow reads and parses workspace-authored YAML and referenced facet files directly from user-controlled paths (
.ff15/operations/<file>.yamlandinstruction.file/output_contracts.report[].format.file), so an outsider authoring those files can inject arbitrary free text into the LLM-bound instruction content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata