web-security-scanner-pro
Fail
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches code from a third-party GitHub repository (
github.com/miladrezanezhad/web-security-scanner-pro.git) that is not identified as a trusted organization or well-known service. - [REMOTE_CODE_EXECUTION]: Instructions direct the installation of external dependencies and the immediate execution of downloaded Python scripts (
python main.py), creating a high-risk remote code execution vector. - [COMMAND_EXECUTION]: The skill requires manual shell command execution for cloning repositories, installing packages via pip, and running the scanner application.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites which could contain malicious instructions.
- Ingestion points:
CustomScanModule.runinSKILL.mdcaptures external responses viaself.browser.get(target). - Boundary markers: Absent. There are no instructions to the agent to ignore or delimit embedded instructions within the scanned web content.
- Capability inventory: The skill possesses network access (
requests), file writing capabilities (results.export_json), and local code execution capabilities (python main.py). - Sanitization: Absent. There is no evidence of filtering or sanitizing HTML/JS content before processing or reporting results.
Recommendations
- AI detected serious security threats
Audit Metadata