deck-swiss-international
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the instructions or configuration. The skill is configured with 'allow_implicit_invocation: false', which is a recommended safety practice to ensure the tool is only used when explicitly requested by the user.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided messages to generate design briefs, creating a potential surface for indirect injection if malicious instructions are embedded in the user's design requests.
- Ingestion points: User message content is used as a brief for the 'prepare_open_design_brief' tool in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: The skill utilizes file-editing tools and registers artifacts via an MCP design server.
- Sanitization: Not explicitly defined in the skill instructions; relies on the agent's internal reasoning and the design tool's processing.
Audit Metadata