asreview-screening
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly shows exporting and ingesting Semantic Scholar / OpenAlex search results (see "Export from Search Results" and the workflow diagram "literature-search → export results → asreview-screening" and ASReviewData.from_file("papers.csv")), meaning it reads public third-party titles/abstracts as part of its active-learning workflow which can materially influence screening decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata