operating-havoc-c2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes a plaintext operator password ("ChangeMe_Str0ng!") in the example Yaotl profile, which is a secret value that the LLM might be required or tempted to reproduce verbatim (high exfiltration risk).

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These URLs point to the Havoc C2 project's GitHub repository (and its profiles subtree) — a public source for building and distributing evasive command‑and‑control agents/payloads — making them a high‑risk download/distribution source for malware-like binaries.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This repository documents and automates an offensive command-and-control framework (Havoc) with explicit payload generation, in-memory execution, process injection, file transfer/exfiltration, pivoting, and evasion/OPSEC guidance — capabilities clearly intended for abuse outside authorized use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs cloning and building the Havoc repository from https://github.com/HavocFramework/Havoc.git (git clone ... then make / run ./havoc), which fetches remote code that is built and executed as a required runtime dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs running "sudo apt ... install" and notes that launching the team server / binding privileged ports (e.g., PortBind 443) may require sudo, which pushes the agent to obtain elevated privileges and modify the host system state.