developer-hub
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an orchestrator that takes user-provided problem descriptions and interpolates them into prompt templates for specialist agents. It mitigates injection risks by enforcing a specific prompt structure and requiring specialists to output findings in a predefined JSON schema format.
- [COMMAND_EXECUTION]: The skill automates report generation by executing a local Node.js script located at
skills/a11y-core/scripts/render-report.mjs. This script is part of the skill's internal toolset and is used to process structured data into human-readable reports.
Audit Metadata