phishing-sim

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.85). High-risk dual-use content: the document provides operational instructions for registering lookalike/squatted sender domains, configuring SPF/DKIM/DMARC to evade rejection, using OSINT for spear-phishing, and infrastructure for tracking and capturing credentials — all patterns that directly enable targeted credential theft and delivery/evasion of email defenses.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly accepts OSINT from a "recon-agent" (employee OSINT output such as LinkedIn titles and project references) as input for spear-phishing, so it clearly ingests untrusted, user-generated public web content and uses it to drive targeting and campaign actions (see the "handoff from recon-agent" and "spear-phishing with OSINT input" lines).