The Agent Skills Directory

[SAFE]: No evidence of malicious behavior, such as credential harvesting, unauthorized network activity, or persistence mechanisms, was found. The skill's instructions are entirely focused on Improving software accessibility and conformance with global standards.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface for indirect prompt injection because its core function involves reading and processing external code and design files. 1. Ingestion points: Source code, UI components, and design specifications accessed via read_file and search_code tools. 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed data. 3. Capability inventory: The agent is authorized to use write_file, edit_file, create_file, execute_command, run_tests, run_linter, and run_build. 4. Sanitization: No specific sanitization or validation of the audited content is required before processing.

accessibility-review