spectra-spec
Fail
Audited by Snyk on Mar 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.80). The prompt includes a directive ("NEVER mention AI or AI-generated code") that instructs concealment of provenance, which is a deceptive behavior unrelated to the stated goal of comparing a spec to an implemented codebase.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata