ai-rag-pipeline

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.85). The set includes an unfamiliar domain that instructs users to run a remote shell installer (curl ... | sh) — a high-risk pattern for malware distribution even though other links are docs/images or placeholders.

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web searches and extracts URL content from open/public sources using tools like tavily/search-assistant, exa/search, tavily/extract and exa/extract, then injects those untrusted search results and page contents into LLM prompts—exposing the agent to indirect prompt injection.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 03:09 AM