tplmap

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is explicitly an exploitation tool: it contains automated SSTI detection and payloads to achieve remote code execution (including interactive OS shells, arbitrary command execution, file upload/download, and payloads to dump app config/classes), which enables unauthorized 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). The SKILL.md shows the tool fetches and interprets responses from arbitrary target URLs (e.g., "python2 tplmap.py -u 'http://target.com/page?name=*'") and uses those untrusted webpage responses to detect/exploit SSTI and drive actions like --os-shell, so third‑party content can influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Start instructs to git clone and run code from https://github.com/epinna/tplmap (git clone https://github.com/epinna/tplmap then python2 tplmap.py), which fetches remote code and executes it as a required runtime dependency.