mineru-api
Warn
Audited by Snyk on Mar 25, 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 accepts and fetches arbitrary file URLs (see SKILL.md "解析单个 URL 文件" and scripts/parse_single.py using client.parse_url and scripts/parse_local.py which downloads the task full_zip_url and extracts .md content), so untrusted third-party content is ingested and returned as Markdown that could influence subsequent agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata