exploit-development

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that embed cookie/session values and JavaScript that exfiltrates document.cookie (e.g., --cookie="session=abc123" and fetch(...+document.cookie)), which forces any agent instantiating these commands to include secret tokens verbatim in output/commands.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Multiple entries are attacker-controlled hosts offering direct downloads of executables/scripts ( .exe, .ps1, .hta, .sct ) and exfil endpoints — clear high-risk indicators for malware distribution (plus a third-party GitHub clone reference used to pull tooling).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skillpack explicitly instructs and automates offensive operations (reverse shells, payload generation, credential harvesting, persistence, exfiltration, MITM/ARP spoofing, cloud metadata theft, and evasion), indicating deliberate malicious capability and intent.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly instructs the agent to bypass security controls (WAF/AV/AMSI), perform privilege escalation and persistence, and run payloads/reverse shells without asking for additional permission—actions that directly modify or compromise the machine's state.