using-superpowers
Fail
Audited by Snyk on Jun 26, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.90). The prompt mandates a global, pre-response workflow and forces execution/announcing of arbitrary "skills" (including running skill files) in a way that overrides the agent's normal instruction hierarchy, which is a deceptive control-of-behavior prompt injection outside a simple "getting started" helper.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata