prompt-focus
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a Python script to process history logs and generate HTML reports. These operations are performed locally using standard system calls.
- [DATA_EXPOSURE]: The script reads sensitive local files containing prompt history. The implementation focuses on data aggregation (word counts, project categorization) and does not persist or exfiltrate raw prompt text.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data from history logs. It implements proper sanitization through JSON parsing and HTML escaping, and it lacks capabilities such as network access that could be maliciously steered by processed content.
- [SAFE]: No malicious patterns, remote code downloads, or obfuscation were identified. The code operates entirely offline using only the Python standard library.
Audit Metadata