Command Development
Warn
Audited by Snyk on Feb 15, 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 includes commands that fetch and ingest user-generated content from third-party services (e.g., "gh pr view $1" / "gh pr diff $1" in references/advanced-workflows.md and examples/plugin-commands.md), so the agent will read and interpret GitHub PRs/comments (untrusted third‑party content) as part of its workflow.
Audit Metadata