command-development

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's examples and workflows explicitly run GitHub CLI to fetch PR content (e.g., "Fetch PR: !gh pr view $1" in SKILL.md and references/advanced-workflows.md), meaning the agent reads user-generated, public GitHub content and uses it to drive reviews and actions, which can enable indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 02:44 AM
Issues
1