design-handoff-brief
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and run thenotuglypackage from the npm registry for color contrast calculations. This is a legitimate tool for accessibility auditing. - [COMMAND_EXECUTION]: The skill executes shell commands to perform contrast checks (
notugly fix) and generate accessibility reports (notugly onepager). These operations are hardcoded and limited to the skill's documented accessibility audit functions. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied Feature Briefs and PRDs, representing an attack surface for indirect injection. [Ingestion points]: Untrusted data enters via the feature brief or PRD notes. [Boundary markers]: There are no explicit delimiters used to isolate user input from skill instructions. [Capability inventory]: The skill has the ability to execute shell commands via
npxand write a review file (review.html). [Sanitization]: The skill does not describe any specific input sanitization or validation steps before processing.
Audit Metadata