phishing-pretext

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains instructions and workflows specifically designed to research and draft target-specific phishing email pretexts and lures.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow involves active web searches and reading public web pages to gather background information and phrasing, representing low-risk ingestion of external content.