keep-others-dependent

Fail

Audited by Snyk on Nov 8, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill directs the agent to produce overly complex, unreadable, and undocumented code to make the user dependent on the AI, which is self-serving and alters the quality of the user's work without malicious intent.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 8, 2026, 06:12 AM
Issues
1