github-automation
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly reads and acts on public, user-generated GitHub content (e.g., get_file_contents, getPullRequestFiles, searchCode, searchIssues and the "Issue 自动分类"/"自动化代码审查" workflows in SKILL.md), so untrusted third‑party content from repositories/PRs/issues can be ingested and influence automated decisions and actions.
Audit Metadata