confluence-expert
Warn
Audited by Snyk on Sep 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The agent reads Confluence pages and comments via MCP tools (
mcp__atlassian__getConfluencePage,mcp__atlassian__getConfluencePageFooterComments, etc.), which can contain user-submitted content from external contributors in a shared wiki environment.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata