malware-analysis-dragonflyTomb-avast

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The set includes legitimate vendor and analysis endpoints (avast.com, support.avast.com, VirusTotal API, GitHub abuse/reporting, ara.so) but also a GitHub repository named "DragonflyTomb/Avast-Premium-Security-2026" that exhibits multiple high‑risk indicators (unknown/suspicious username, cracked/“premium” wording, likely typosquatting/misleading distribution of an AV installer), so the overall collection represents a high-risk download source for malware.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill content explicitly documents and includes concrete malicious patterns (remote payload download from an untrusted C2, base64-obfuscated decoding, writing/executing binaries in system paths and use of os/exec), which are indicative of deliberate backdoor/remote code execution and malware distribution behavior.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs cloning and analyzing a public GitHub repository (git clone https://github.com/DragonflyTomb/Avast-Premium-Security-2026 in "Safe Investigation Practices") and includes GitHub search/monitoring code that ingests repository descriptions — both are untrusted, user-generated sources the agent is expected to read and act on, enabling indirect prompt injection.