pr-review-canvas
Warn
Audited by Snyk on Jun 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Outsider-authored PR content (e.g., PR title/body, file patches, and PR review comments written by the GitHub PR author/others) is fetched at runtime via
gh api repos/{owner}/{repo}/pulls/{number}...//files//comments, then embedded as readable HTML and diff text intotemplate.html(including thepr-diffs-json<script type="application/json">payload) and rendered byrenderer.jsinto the agent’s LLM-visible context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata