spec-discovery
Fail
Audited by Snyk on Aug 24, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.70). The skill includes explicit override instructions (e.g., "Ignore Claude-specific mode-switch instructions") and global workflow directives that tell the agent to auto-execute or auto-select skills without honoring external/system/user mode switches, which are attempts to override other system instructions and thus constitute a prompt-injection risk outside the spec-discovery's stated task.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata