cursor-context-management
Warn
Audited by Snyk on Apr 4, 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 "On-Demand (explicit @-mention)" and "Using External Knowledge" sections explicitly allow @Web (live web search results) and @Docs (crawled external documentation) to be added to the agent's context, meaning the agent fetches and reads third-party web content that can influence its behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata