do-design-system
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow requires the agent to execute shell commands for environment discovery and automated verification. This includes using
git rev-parse --show-toplevelto identify the project root and usingcurlandgrepto verify the accessibility and content of the generated style-guide page. These operations are intended for local project management and testing purposes. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the project (such as
package.json, identity files, and existing design tokens) and user-supplied configuration overrides via$ARGUMENTS. This content is used to generate theDESIGN.mdfile and the style-guide page, creating a surface where malicious input could influence the agent's behavior or output. - Ingestion points: Project configuration files (
package.json,site.ts, etc.) and the$ARGUMENTSoverride string, as described inreferences/design-spec.md. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying instructions embedded within the ingested project data.
- Capability inventory: The skill utilizes file system read/write access and local shell command execution (
git,curl,grep). - Sanitization: No explicit sanitization or validation of the input data is defined in the skill instructions.
Audit Metadata