nvda-addon-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference for developing screen reader add-ons. It provides architectural diagrams, code examples for the
@scriptdecorator, and a set of audit rules for identifying common errors and security vulnerabilities in add-on code (e.g., Rule NVDA-016 for secure mode checks). - [EXTERNAL_DOWNLOADS]: All external links point to official or well-known community resources, including the NVDA source code on GitHub (
github.com/nvaccess), the community add-on documentation (github.com/nvdaaddons), and the official NV Access website. These are domain-specific trusted sources and do not include any remote code execution patterns. - [PROMPT_INJECTION]: The instructions focus entirely on technical domain expertise and behavioral constraints for providing accurate guidance. There are no patterns suggesting attempts to bypass safety filters or override agent behavior.
- [DATA_EXFILTRATION]: No sensitive file paths, credential markers, or suspicious network operations were identified. The skill correctly recommends checking
shouldWriteToDisk()before performing file operations, adhering to NVDA's secure mode best practices.
Audit Metadata