scientific-writing
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires using the research-lookup skill and running web searches/extractions (e.g., the "Stage 1: Use the research-lookup skill" workflow and the "Post-Writing Citation Metadata Check" which calls parallel_web.py search and parallel_web.py extract against https://doi.org/DOI) to fetch and ingest public third-party web content that the agent must read and act on.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata