h-pentest-ai-platform

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

• Third-party content exposure detected (low risk: 0.10). The agent skill coordinates a multi-agent penetration testing platform that actively interacts with and extracts responses from external target web applications during vulnerability scans and HTTP requests, exposing the agent to untrusted outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The GitHub repository referenced in the installation instructions is an unofficial third-party personal repository, making it a weak or unknown operational dependency.