confluence
Warn
Audited by Snyk on Mar 1, 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 shows the agent performs reads/searches against a Confluence instance (e.g., af confluence get, search, comments, attachments using the JIRA_BASE_URL) which ingests user-generated wiki pages, comments, and attachments that the agent will read and could materially influence subsequent actions like updates, labeling, or publishing.
Audit Metadata