light-kanban-worker

Warn

Audited by Snyk on Aug 19, 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). SKILL.md’s required runtime workflow reads free text fields from board-supplied tasks (e.g., “Read task + project instructions”, including title, description, tags, reviewFeedback, and “Follow the host and project's existing instruction priority”) via GET /api/tasks?status=in_progress, GET /api/tasks?status=todo, and then loads AGENTS.md/README-like project files from the claimed task workspace, where those task/project texts are outsider-authored and are consumed by the worker without first selecting a specific trusted item.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 19, 2026, 08:07 AM
Issues
1