service-design-workshop
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of informational markdown files and configuration. It does not invoke any external tools, perform network operations, or execute code. All logic is contained within static instructions and local reference documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user-provided service design challenges and materials.
- Ingestion points: User-provided service design problems, requirements, and existing materials processed via
SKILL.md. - Boundary markers: None identified; user input is processed naturally within the provided templates.
- Capability inventory: No risky capabilities. The skill does not have access to shell execution, network tools, or sensitive file system operations. It only generates Traditional Chinese Markdown text.
- Sanitization: Not present, but risks are mitigated by the lack of actionable capabilities.
Audit Metadata