Command Development
Warn
Audited by Snyk on Feb 17, 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 instructs the agent to run third-party fetches such as GitHub CLI commands (e.g., "gh pr view", "gh pr diff", "gh pr checks") and similar bash-tool invocations that load PRs/changes and other user-generated content from public repositories, so the agent will read and interpret untrusted, user-generated third‑party content as part of its workflow.
Audit Metadata