accessibility
Pass
Audited by Gen Agent Trust Hub on Jun 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Node.js and shell scripts (
accessibility-audit.mjs,check-accessibility.mjs,install-accessibility-hooks.sh) used for generating documentation and performing static analysis of codebases for accessibility signals. These scripts perform standard file system operations within the local project context. - [DATA_EXFILTRATION]: No network exfiltration or unauthorized access to sensitive data was detected. The scripts are focused on local file operations, such as reading source files for pattern matching and writing documentation to the
docs/directory. - [PROMPT_INJECTION]: The instructions in
SKILL.mdare correctly scoped to accessibility best practices. No attempts to override agent constraints, bypass safety filters, or extract system prompts were identified. - [EXTERNAL_DOWNLOADS]: The README provides standard installation instructions using official package managers (npm, yarn). No scripts within the skill perform remote code execution or download content from untrusted sources.
- [PERSISTENCE_MECHANISMS]: The skill includes a script to install Git hooks (
install-accessibility-hooks.sh). While this provides automated execution, it is used for the documented purpose of running accessibility checks before code pushes, which is a common and legitimate development workflow.
Audit Metadata