implement-design
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill is designed to ingest and process data from external Figma files, which could theoretically contain malicious instructions embedded in text layers or metadata.\n
- Ingestion points: Untrusted design data enters the context via get_design_context and get_metadata tool outputs (defined in SKILL.md).\n
- Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions found within the design data.\n
- Capability inventory: The skill allows for the creation and modification of project source code files based on the ingested data.\n
- Sanitization: No explicit sanitization or validation logic is defined for the external design data before it is processed for code generation.
Audit Metadata