github-wrapped
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill uses local shell and Python scripts to automate data collection via the GitHub CLI and perform data transformation. No execution of untrusted or remote code was detected.- DATA_EXPOSURE (SAFE): The skill accesses GitHub account data which is the intended functionality. Data is stored locally in a user-defined directory and is not exfiltrated to external servers.- PROMPT_INJECTION (SAFE): The instructions are focused on task execution and do not contain patterns aimed at bypassing agent safety filters or overriding system instructions.- INDIRECT_PROMPT_INJECTION (SAFE): Although the skill processes external data from GitHub APIs, it implements proper sanitization by escaping HTML-sensitive characters (e.g., converting '<' to '\u003c') before embedding the data into the final HTML report.
Audit Metadata