hello-world
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.90). The workflow includes an explicit step to run a script that collects the user's system information, which is unrelated to the skill's advertised simple greeting purpose and thus constitutes deceptive/out-of-scope data-collection instructions.
Audit Metadata