constructive-ai
Warn
Audited by Snyk on Apr 3, 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 includes CI/install steps that run a remote install script (curl -fsSL https://ollama.com/install.sh | sh) during workflow runtime, which fetches and executes remote code and is relied on to install Ollama.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata