executing-red-team-engagement-planning

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content is a dual-use red-team engagement planner that explicitly documents and automates offensive capabilities (phishing, C2 infrastructure, implants/backdoors, persistence mechanisms, credential harvesting, exfiltration techniques, log tampering/timestomping, and domain/SSL setup) which could be directly repurposed for malicious attacks even though the provided scripts themselves only generate planning documents rather than executing attacks.

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly instruct ingesting open/public third‑party content — e.g., "Pull industry-specific threat reports (Mandiant M‑Trends, CrowdStrike...)" and "OSINT collection" / "Social media profiling of target personnel" in references/workflows.md and SKILL.md — meaning the agent is expected to read untrusted, user‑generated web/social content that can materially influence planning decisions.