start-learning
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). SKILL.md describes an onboarding flow where the agent asks the learner “Why are you learning AI engineering? Free text” and then writes that user-provided free text into LEARNING.md (runtime input/output path is the user interview, not first-party documentation).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata