pretext-brainstormer

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill is designed to generate social engineering pretexts and phishing ideas tailored to target organizations, which presents a direct security risk regarding malicious simulation and potential real-world harm.

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

• Third-party content exposure detected (low risk: 0.10). The workflow requires the agent to research recent news, blog posts, press releases, and public notices regarding a target organization, which involves ingesting arbitrary public web pages and outsider-authored text.