research-writing-assistant
Warn
Audited by Snyk on Jul 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该技能的 required workflow(文献综述)会在运行时通过 WebSearch/WebFetch/脚本
scripts/scholar_search.py获取并处理外部网页/数据库返回的可读文本(如标题、摘要、DOI元数据),从而把“非用户选择引入”的第三方内容注入到 LLM 上下文中。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The environment-setup skill downloads and executes remote Miniconda installer(s) at runtime (e.g., https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh and related URLs), which fetches and runs external executable code necessary for the skill.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata