voice-editor

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs routine text processing and editing tasks within the agent's environment.
  • [DATA_EXFILTRATION]: The skill requests access to a configuration file path (~/.claude/voice/VOICE.md) to retrieve a voice profile. This is consistent with the skill's stated purpose of style alignment and does not involve any network operations to exfiltrate data or access sensitive credentials.
  • [PROMPT_INJECTION]: There are no instructions that attempt to bypass AI safety filters or override system-level constraints. The instructions are focused on guiding the editing process.
  • [REMOTE_CODE_EXECUTION]: No patterns for remote script execution, package installation, or dynamic code generation were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 09:57 AM