executing-red-team-engagement-planning

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk dual‑use content: although framed for authorized red‑team work, the skill explicitly documents and templates operational techniques for persistence/backdoors, credential theft (LSASS, Kerberoasting, password spraying), data exfiltration, supply‑chain compromise, C2 infrastructure (Cobalt Strike, redirectors), OPSEC evasion (timestomping, log cleanup, rotating C2), and physical/social intrusion — all of which are deliberate malicious capabilities that can be abused if used without legal authorization.

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs pulling external OSINT and industry threat reports and mapping MITRE ATT&CK data (see SKILL.md and references/workflows.md "Pull industry-specific threat reports" and references/api-reference.md which shows GET https://raw.githubusercontent.com/mitre/cti/master/enterprise-attack/enterprise-attack.json), so it requires ingesting untrusted public third-party content that could influence decision-making.