long-context

Warn

Audited by Snyk on Jul 31, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill explicitly performs a runtime git clone and then runs Python training scripts from the fetched repository https://github.com/jquesnelle/yarn (used in the YaRN fine-tuning steps), which fetches and executes remote code required for the skill.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 31, 2026, 09:36 PM
Issues
1
Security Audit — snyk — long-context