create-branch

Warn

Audited by Snyk on Feb 17, 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). This skill calls GitHub CLI (gh issue view ) and auto-generates branch names from the returned GitHub issue title (user-generated, public content), so it ingests untrusted third-party content that the agent reads and interprets.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 10:21 PM