github-auth
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- Data Exposure & Exfiltration (MEDIUM): The skill instructions read credentials from a .env file, which is a sensitive file path.
- Evidence: use of grep and Get-Content on .env.
- Severity downgraded from HIGH because this is the primary purpose of the skill.
- Data Exposure & Exfiltration (MEDIUM): The skill provides an example of embedding credentials in a URL, which can lead to leaks in history and logs.
- Evidence: git clone URL with PAT.
- Command Execution (LOW): The skill executes shell commands using gh, git, and curl to manage repositories.
- Evidence: various commands in SKILL.md and SKILL.json.
Audit Metadata