red-team-ops

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is high-risk: it provides explicit, actionable offensive instructions (reverse shells, msfvenom payloads, Meterpreter post‑exploitation like hashdump and keylogging, persistence, evasion, and exfiltration) that enable system compromise, credential theft, and covert remote access despite stated ethical boundaries.

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow (references/tools.md) explicitly instructs fetching and ingesting public web content—e.g., waybackurls target.com, gau/waybackurls, curl to bgp.he.net, httpx/amass outputs—so untrusted, user-generated/open-web data is read and used to guide subsequent tool actions.