red-team

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This repository provides explicit, actionable offensive tradecraft (credential dumping guidance, exfiltration methods, C2/opsec evasion, AMSI bypass, obfuscation advice) that directly enables malicious activity even though framed as "authorized" red‑team use.

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/engagement_planner.py, the runtime workflow only ingests outsider-provided CLI free text via --techniques, --access-level, and --crown-jewels (which directly flow into plan generation/scoring) after a gate on --authorized, but the core planning does not require selecting any pre-existing first-party item.