literature-filtering
Warn
Audited by Snyk on Aug 1, 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). In SKILL.md, the workflow only reads outsider-authored free text from a user-supplied input CSV via read_input_csv(path), then concatenates title and abstract for keyword screening (screen_record), so attackers can poison the input dataset.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata