Hoshinkanri
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of markdown files (
SKILL.mdand various templates in thetemplates/directory). No executable scripts (Python, JavaScript, Shell) are present. - [Command Execution] (SAFE): There are no instances of subprocess spawning, shell command execution, or system calls.
- [Data Exfiltration] (SAFE): No network operations (e.g., curl, wget, fetch) or external data transmission patterns were identified.
- [Prompt Injection] (SAFE): The instructions are focused on guiding the agent through business process methodologies. No attempts to override safety filters or bypass system instructions were detected.
- [Indirect Prompt Injection] (LOW): The skill ingests user-provided strategic data (objectives, KPIs) to populate templates. However, as there are no 'write' or 'execute' capabilities, this represents a negligible attack surface.
Audit Metadata