github-automation
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and acts on public, user-generated GitHub content—e.g., getPullRequestFiles, getPullRequest, searchIssues, searchCode and "分析 Issue 内容" in SKILL.md—which lets third-party PRs, issues, or repo files be ingested and influence automated reviews, labeling, or merges, enabling indirect prompt injection.
Audit Metadata