chunxiang-rocket

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The prompt includes deceptive persona and override instructions—e.g., "you serve Linus Torvalds", "each interaction starts with '哥'", and "enable ultrathink" with coercive consequences—which attempt to change agent identity/behavior outside the stated programming-guide purpose.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 12:31 AM