bkend-data

Warn

Audited by Snyk on Mar 7, 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). The SKILL.md explicitly directs the agent to fetch live documentation via WebFetch from raw.githubusercontent.com (see "Official Documentation (Live Reference)"), which means the agent will retrieve and interpret public, user-hosted third-party content that could influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 05:56 PM