pie-design-system
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local utility script,
scripts/fetch-references.mjs. This script facilitates the synchronization of components, guides, and design token metadata from the user's locally installed@justeattakeawayand@justeatpackages into the skill's internal reference directory. - [INDIRECT_PROMPT_INJECTION]: The skill populates its context with external documentation files retrieved from the user's project environment, which presents a surface for indirect instructions.
- Ingestion points: Documentation files (READMEs and guides) and JSON metadata are copied by the
fetch-references.mjsscript from thenode_modulesdirectory of the consumer project. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the ingested reference content.
- Capability inventory: The agent is authorized to run the provided script, which performs file system read and write operations within the project and skill scope.
- Sanitization: There is no evidence of sanitization or content validation for the documentation files before they are presented to the agent's context.
Audit Metadata