use-graphite

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: 0.70). This skill explicitly instructs the agent to read PR descriptions via "gh pr view <PR_NUMBER> --json body --jq '.body'", which fetches user-generated content from GitHub (an untrusted third-party source) and expects the agent to interpret it as part of the workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:22 AM