announce

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: 0.90). The skill explicitly fetches PRs, issues, and release notes from GitHub using the GitHub CLI (commands like "gh pr list", "gh issue list", and "gh release view"), ingesting user-generated/untrusted content (PR/issue titles and bodies) that the agent will read and synthesize.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:36 PM