lfisuite

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These URLs contain explicit LFI/path-traversal payloads targeting /etc/passwd and link to a small, suspicious GitHub repo for an LFI exploitation tool — strong indicators of active exploitation capability and potential for RCE/malware distribution.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly documents and automates Local File Inclusion exploitation (path traversal, log poisoning, php wrappers, RFI and /proc inclusion) to achieve remote code execution and read sensitive files (e.g., /etc/passwd), indicating intentional malicious/abusive functionality for system compromise and data exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and includes content from arbitrary remote web targets (e.g., examples like "http://target.com/page.php?file=..." and the "Remote file inclusion (RFI)" option in SKILL.md), meaning untrusted third-party content would be read and can materially change behavior (e.g., execute included PHP), so it exposes the agent to indirect prompt/instruction injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The Quick Start explicitly instructs cloning and running remote code from https://github.com/D35m0nd142/LFISuite, which is fetched at runtime and executed (python3 lfisuite.py), so the external URL provides code that directly executes and is a required dependency.