personal-writing-style

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown files. There are no executable scripts, shell commands, or configuration files that initiate network connections or file system modifications.
  • [SAFE]: No obfuscation, data exfiltration, or credential harvesting patterns were detected. All content is human-readable and focused on linguistic preferences.
  • [SAFE]: Although the term 'prompt injection' appears in references/punctuation.md, it is used strictly within a benign example sentence to demonstrate punctuation usage ('Clawdbot documentation recommends Opus 4.5... better prompt injection resistance'). It is not an instruction to bypass safety filters or override agent behavior.
  • [SAFE]: The skill does not define any external dependencies or download remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 03:43 PM