issue-reply

Warn

Audited by Snyk on Feb 27, 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 explicitly reads full GitHub issue text and all comments via gh issue view $ARGUMENTS --comments --repo [REPO] (user-generated, public third‑party content) and then uses that content to decide and draft replies and post comments, so untrusted issue content could indirectly inject instructions affecting agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:57 AM