data-synthesis
Warn
Audited by Snyk on Aug 12, 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). SKILL.md’s core loop requires ingesting “RAW DATA (Excel, CSV, stickies)” via runtime commands like
memi research from-file <path>/from-stickies, where the raw observations (“text, source, participant?, timestamp?”) are read and coded at L52-53 and then harvested as individual observations at L23.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata