component-decision-tree
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest component names, descriptions, and variant data from external sources to build decision trees.
- Ingestion points: Data is pulled from the Figma MCP integration (file_key), Storybook index, and local codebase inventory files (
.ai/index/component-inventory.yml). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded within component descriptions.
- Capability inventory: The skill possesses the
Writecapability to create Markdown and YAML files based on the ingested data, and utilizes restrictedBashtools (cat,ls,find,head) for file inspection. - Sanitization: There are no explicit requirements to sanitize or escape the content retrieved from external integrations before it is interpolated into the generated documentation or YAML trees.
Audit Metadata