research-summarizer
Warn
Audited by Snyk on Aug 21, 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 the required workflow for
/research:summarize,/research:compare, and/research:cite, the skill ingests user-provided documents/text (e.g., “Summarize this paper/article… Extract citations from this PDF” and “Scan document for all references”), meaning outsider-authored free text can be read by the model as the “single/multi source” content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata