implement-from-design
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external design tools.
- Ingestion points: Untrusted design context is retrieved from Figma, Sketch, MasterGo, Pixso, and Modao via MCP integrations or user-provided screenshots (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or specify that content within design files should be treated purely as data, which may lead the agent to follow instructions embedded in design layers.
- Capability inventory: The skill allows the agent to read project files, write new files to the
reports/directory, and execute shell commands for linting and testing. - Sanitization: There is no mechanism described for sanitizing or escaping the text content extracted from design files before it influences the agent's implementation plan or file operations.
Audit Metadata