daily-paper-generator
Warn
Audited by Snyk on May 17, 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). The SKILL.md workflow explicitly instructs the agent to use a Chrome MCP browser to search and retrieve metadata/abstracts from public sites (arXiv, NBER, and journal TOC pages listed under "Sources to Search"), so the agent will ingest untrusted, user-generated/public web content as part of its evaluation and selection logic, creating a clear risk of indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata