aliyun-docmind-extract
Warn
Audited by Snyk on Apr 29, 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's quickstart and scripts (SKILL.md quickstart, scripts/quickstart.js) submit arbitrary public URLs via DOCMIND_FILE_URL / submitByUrl to DocMind, which ingests and returns parsed document content that the agent is expected to read and act on, enabling untrusted third-party (public web) content to influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata