categorize-papers
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 (medium risk: 0.65). The required workflow spawns a subagent (via the “subagent-spawning/spawn-agent skill”) that reads the provided
paper_listcontaining outsiders’ paper abstracts/keywords (free-form prose) into its LLM context for clustering, creating an indirect prompt-injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata