merlin

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that pass secrets verbatim on the command line (e.g., -psk "passphrase"), which instructs the agent to embed sensitive values directly in generated commands and is therefore insecure.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These links point to a command‑and‑control (C2) endpoint placeholders and a GitHub releases page for "Merlin" — a known C2/implant framework with prebuilt executables and explicit instructions to generate/run agents and credential‑stealing modules, making them a high‑risk distribution vector for malware.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). Merlin is an explicit command-and-control framework: it provides covert transports (h2c/h3/QUIC/DNS), remote command execution, file upload/download, session interaction, and modules like Mimikatz for credential dumping — all clear indicators of backdoor, data-exfiltration, and system-compromise intent.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs downloading and executing binaries from https://github.com/Ne0nd0g/merlin/releases and configures agents to connect to runtime C2 endpoints (e.g., https://C2:443/ and https://C2:8443/) which deliver remote commands that control and execute code on agents.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This prompt instructs the operator to download and run a remote C2 server and agents (including running binaries, binding to privileged ports, executing shell commands, uploading/downloading files and running Mimikatz), which directly enables altering the host state and performing privileged/credential-theft operations, so it should be flagged.