capabilities

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of static Markdown documentation. There are no executable scripts, shell commands, or network requests present in the files.
  • PROMPT_INJECTION (SAFE): No instructions targeting agent behavior override, role-play injection, or safety filter bypasses were detected.
  • DATA_EXFILTRATION (SAFE): No sensitive file paths, credential patterns, or network communication commands are present.
  • EXTERNAL_DOWNLOADS (SAFE): There are no remote downloads or external dependencies referenced beyond a static link to a legitimate government portal (nta.go.jp).
  • INDIRECT_PROMPT_INJECTION (LOW): While the skill uses a template placeholder {ペルソナ名} for output generation, the lack of tool execution capabilities or data ingestion means there is no path for this to escalate into a vulnerability.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 11:14 PM