anti-ai-writing

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of instructional text focused on improving Vietnamese writing style and tone. It serves as a baseline for generating more human-like content.
  • [NO_CODE]: There are no scripts, binaries, or executable code sections within the skill. It relies purely on the agent's linguistic capabilities.
  • [EXTERNAL_DOWNLOADS]: No external URLs or remote resources are referenced or downloaded.
  • [PROMPT_INJECTION]: The instructions do not attempt to override system prompts, bypass safety filters, or extract sensitive model information. It uses natural instructional language to define writing constraints.
  • [DATA_EXFILTRATION]: The skill does not access local files, environment variables, or credentials, nor does it perform any network requests.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 07:22 AM