pentestcode-ai-pentest-agent

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill defines a penetration testing agent that can parse untrusted scan results and tool outputs (like nmap XML, Nuclei JSON, etc.) and ingest target data/web content during security assessments, presenting indirect prompt injection risks.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions explicitly direct fetching and executing a remote shell script from GitHub (https://raw.githubusercontent.com/s0ld13rr/pentestcode/main/install.sh), which constitutes an external runtime operational dependency with third-party/personal provenance.