bailian-knowledge

Fail

Audited by Snyk on Jun 20, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.70). Most links are to a personal GitHub repo (konglong87/rag_skills_ali) plus badge/claude.ai pages; while not obviously malicious, the project advertises precompiled binaries that require Alibaba Cloud AK/SK in a local config—downloading/running unvetted binaries from an individual GitHub account (especially ones that handle secrets) is risky and could enable credential exfiltration or malware.

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

  • Third-party content exposure detected (high risk: 0.85). 该技能在运行时调用阿里云百炼 RetrieveWithOptions 获取知识库检索结果,随后将返回的 resp.Body(其中包含 Data.Nodes[].Text 等自由文本)作为可读文本输出给下游 LLM 上下文;这些 Text/doc_name/doc_url 来自外部知识库内容,属于非操作用户选择引入的第三方文档来源。

Issues (2)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jun 20, 2026, 10:37 PM
Issues
2
Security Audit — snyk — bailian-knowledge