model-validation
Warn
Audited by Snyk on Aug 11, 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 runtime workflow reads outsider-authored free text from the user-supplied split-assignment CSV passed to
python3 ${CLAUDE_SKILL_DIR}/scripts/check_split_leakage.py --splits <split_assignment.csv>, and the script parses CSV columns and values (e.g., patient IDs, split labels, seed text), exposing it to indirect prompt-injection via arbitrary text fields.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata