start

Warn

Audited by Snyk on Jun 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). In EXISTING ISSUE mode, the skill calls gh issue view <number> --json number,title,body,... and then displays/uses the issue body (user-submitted GitHub text from an outsider) as readable LLM context, creating an indirect prompt-injection path.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 11:14 AM
Issues
1
Security Audit — snyk — start