vector-search-patterns

Warn

Audited by Snyk on Nov 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The RAG pipeline (search, then feed retrieved chunks into the LLM prompt) reads from a vector store the user populates, which may contain outsider-authored text such as ingested web or user content, but the skill names no specific outsider-writable feed and the agent does not need to fetch arbitrary content itself.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 15, 2026, 11:37 PM
Issues
1