terms-of-service
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of Markdown templates and instructional guidelines. It does not contain any executable code (Python, JavaScript, or shell scripts).
- [DATA_EXPOSURE]: While the skill prompts the user for information like names and email addresses, this data is collected explicitly for populating the legal templates as part of the intended functionality. No attempts to access sensitive system files (e.g., SSH keys, AWS credentials) were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill uses template interpolation (e.g.,
{{サービス名}}) to insert user-provided strings into documents. While this represents a theoretical injection surface, the risk is negligible as the agent's output is restricted to text generation and no high-privilege tools are invoked during the process. - [REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic execution patterns were found. The skill references an external site (kiyaku.jp) as a source of content inspiration, but does not perform network operations to it.
Audit Metadata