NYC

plan-ci

Warn

Audited by Snyk on Feb 16, 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 instructs the planner subagent to read GitHub Actions logs from a provided GitHub Actions URL ($ARGUMENTS), which are public/user-generated third-party artifacts the agent will fetch and interpret, exposing it to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:19 PM