System

Warn

Audited by Snyk on Mar 5, 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). The skill explicitly ingests and analyzes files from a public fork (pai-opencode) in Workflows/CrossRepoValidation.md (and runs SecretScanning/GitPush against the public repo), so it reads untrusted, user-generated repository content locally and uses those findings to drive decisions (block pushes, auto-fix, report), creating a clear avenue for indirect prompt injection via crafted repo content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 07:39 AM