hunt-information-disclosure
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands (curl, wget, jq) and Node.js execution to automate the discovery and analysis of information disclosure vulnerabilities on remote targets.
- [EXTERNAL_DOWNLOADS]: The skill probes for and downloads potentially sensitive files from target web servers, including environment variables (.env), version control metadata (.git), and database configuration files.
- [DATA_EXFILTRATION]: The skill is designed to identify and extract sensitive configuration data, internal paths, and source code from external systems as part of its primary security-hunting function.
- [SAFE]: All identified activities are standard for red-teaming and security auditing purposes and do not indicate malicious intent against the agent or the user's local environment.
Audit Metadata