skills/practicalswan/agent-skills/rag-eval/Snyk

rag-eval

Warn

Audited by Snyk on Sep 9, 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 required workflow directs agents to convert public links, dataset landing pages, and external web content into local corpus files without an automated sanitization step, presenting an indirect prompt injection risk.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 9, 2026, 03:51 AM

Issues

1