pandas-data-manipulation-rules

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The "Memory Protocol" mandates executing a local shell command to read a hidden .claude memory file and to persist discoveries, which is an instruction to access/store external agent state that is unrelated to pandas code-review and thus constitutes a hidden/deceptive instruction outside the skill's stated purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill contains a deliberate "Memory Protocol (MANDATORY)" that instructs reading a local agent memory file (.claude/context/memory/learnings.md) and then recording discoveries — a clear prompt-injection attempt to access and exfiltrate internal memory/state, which constitutes a high-risk backdoor/data-exfiltration pattern.