prisma-screening
Warn
Audited by Snyk on Jul 24, 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). SKILL.md describes a workflow that imports SOPs like
paper-search/paper-researchfor full-text “AI summaries” of candidate papers, which likely requires fetching/reading outsider-authored document text at runtime (e.g., paper full text or metadata from external sources) and inserting it into the agent LLM context for screening.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata