paper-interpretation-flow

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly extracts and ingests papers from user-supplied arXiv URLs, paper URLs, or PDFs ("收集论文列表" and "步骤 A — 读论文") and passes that third-party content into the paper-interpretation tool to be read and acted on, so untrusted external content can influence downstream analysis and card-generation behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 03:17 PM
Issues
1