nativescript

Fail

Audited by Snyk on Mar 3, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The skill contains a "Memory Protocol" that instructs the agent to read a local ".claude/context/memory/learnings.md" file and persist/assume memory across runs—instructions unrelated to NativeScript code review and appearing to access internal/hidden context, which is a deceptive prompt-injection attempt.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 3, 2026, 07:57 AM