npcpy-research-guide
Warn
Audited by Snyk on Apr 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly defines an Agent with tools like "web_search" and "paper_search" and workflow methods (e.g., ResearchWorkflow.literature_review and analyze_paper) that fetch and ingest public web pages and academic papers which the agent reads and uses to drive summaries and actions, exposing it to untrusted third‑party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata