agent-install-guide

Warn

Audited by Snyk on Feb 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The README Integration Template explicitly instructs AI agents to "Fetch and follow instructions from https://raw.githubusercontent.com/user/repo/main/INSTALL.md" (and the raw.githubusercontent.com URL pattern), which is clear evidence an agent would fetch remote content at runtime that directly controls prompts/instructions and would be relied on as a required dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 01:18 PM