polygraph
Warn
Audited by Snyk on Feb 16, 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 delegates to and reads data from external repositories and their pull requests via cloud_polygraph_delegate and cloud_polygraph_get_session (e.g., PR titles/bodies, workspace info, and delegated agent outputs), which are user-generated/untrusted sources that the agent will ingest and display.
Audit Metadata