skills/reason-machines/ai-agent-skills/agentic-harness-engineering/Snyk

agentic-harness-engineering

Warn

Audited by Snyk on Oct 8, 2026

Risk Level: MEDIUM

Full Analysis

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

Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning an unofficial repository from GitHub (china-qijizhifeng/agentic-harness-engineering.git) during setup, constituting an operational dependency with common/reputable unofficial provenance.

Issues (1)

W012

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 8, 2026, 11:38 PM

Issues

1