pstack-show-me-your-work
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local bash script
scripts/log.shto append decision data to a TSV (Tab-Separated Values) file. - Sanitization Logic: The script includes a
clean()function that strips tabs, newlines, and carriage returns to maintain log structure. - Injection Mitigation: The script specifically checks for spreadsheet formula prefixes (
=,+,-,@) and escapes them with a single quote to prevent Formula Injection (CSV Injection) when the log is opened in spreadsheet software like Excel or Google Sheets. - [SAFE]: No malicious patterns, prompt injections, or data exfiltration vectors were detected. The skill's behavior matches its stated purpose of providing an audit trail for agent actions.
Audit Metadata