agentflow

Warn

Audited by Snyk on Apr 14, 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). Yes — the skill's orchestrator and workers explicitly read and act on user-generated Kanban card content and comment threads from external project management tools (Asana, GitHub Projects, Linear) and GitHub PR context, which the agents ingest and use to decide actions and dispatch workers.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 08:34 AM
Issues
1