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
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 16, 2026, 12:40 AM
Issues
1