monitor-ci
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to spawn a subagent that polls Nx Cloud CI attempts and to read/interpret returned third-party content such as taskOutputSummary, suggestedFix/suggestedFixReasoning and selfHealingSkipMessage (CIPE URLs) from the Nx Cloud/CI provider and then apply/reject fixes or run local actions based on that content, exposing the agent to untrusted external content that can influence behavior.
Audit Metadata