voice-preserving-line-edit
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are focused on stylistic prose editing and do not contain any executable scripts or shell commands. It includes explicit directives to 'Lock the source' and preserve facts, numbers, code, commands, and links, which protects the integrity of the input data and prevents unintentional execution or alteration of sensitive content.
- [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, obfuscation, or persistence mechanisms, were detected in any of the skill files.
- [SAFE]: The 'Advisory, not blocking' section correctly defines the behavior for internal prose quality checks and does not attempt to override or bypass AI safety filters.
Audit Metadata