product-sense
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md's "Research-First Workflow" explicitly requires the agent to perform web searches and cite linked sources (e.g., "Use web search... Do 5-10 searches" and "Cite sources — Include linked source inline"), which forces fetching and ingesting open/public third-party content that will be read and used to drive the agent's output and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata