gracker-deep-research

Warn

Audited by Snyk on May 2, 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). Yes — the skill's Phase 1 explicitly requires network searches and archiving of cited URLs ("Phase 1c: 参考资料归档 — 主 session 对所有 cite 的 URL 执行抓取或打开归档" and the research-dump-template's requirement to "精选 3-5 个最有价值的页面,用当前运行时可用方式抓取或打开全文"), so the agent fetches and ingests arbitrary third‑party web content that is then read and used to drive research outputs and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 03:08 PM
Issues
1