agentflow

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors and consumes Kanban board task descriptions, comments, and project management feeds (such as GitHub Projects, Asana, and Linear) where outsiders can post untrusted text and comments.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning and installing from an arbitrary community GitHub repository (UrRhb/agentflow), presenting a high-risk unknown operational dependency.