no-scripted-editing
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional content aimed at improving the reliability and auditability of an AI agent's file modifications.
- [SAFE]: It establishes a behavioral policy that prohibits the use of shell-based scripted editing (e.g., sed, awk, shell redirects) on tracked repository files to prevent silent failures and unreviewable changes.
- [SAFE]: There are no executable scripts, binary files, or external dependencies associated with this skill.
- [SAFE]: The instructions do not involve any network communication, sensitive data access, or attempts to bypass agent safety constraints.
Audit Metadata