code-structural-search

Fail

Audited by Snyk on Mar 6, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The "Memory Protocol (MANDATORY)" section instructs the agent to read and write specific .claude/context/memory files and to "ASSUME INTERRUPTION," which are operational persistence/exfiltration-style directives unrelated to the skill's advertised AST-based search purpose and thus constitute hidden/deceptive instructions outside scope.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 6, 2026, 09:13 AM