literature-review
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 (low risk: 0.10). The skill’s runtime ingests outsider-authored free text only when the user provides a literature query/citation string, which is then used as a search term to fetch provider-owned bibliographic records via CrossRef/OpenAlex and is not directly followed as instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata