benchmark

Warn

Audited by Snyk on May 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: 0.80). SKILL.md Mode 1 ("Navigate to each target URL") explicitly instructs the agent to fetch and measure arbitrary target URLs (public web pages), so untrusted third-party page content is ingested and its extracted metrics are used to produce verdicts/decisions in the workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 19, 2026, 06:50 AM
Issues
1
Security Audit — snyk — benchmark