nav-start

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's Step 6 "Check PM Tool for Assigned Tasks" explicitly runs external PM queries (e.g., gh issue list and checks for Linear/Jira) which fetch user-generated issues from third-party services that the agent will read and interpret, exposing it to untrusted third-party content.