better-accessibility
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and does not contain any executable scripts, binaries, or configuration files that could be used for malicious purposes. No unauthorized network activity or data access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill guides the agent in reviewing and modifying user-provided code, which serves as an ingestion point for potentially untrusted data. This surface could be exploited if malicious instructions are hidden within the code's text or ARIA attributes to influence the agent's behavior during analysis.
- Ingestion points: User-provided UI source code files (HTML, CSS, React/TSX components) and interface descriptions.
- Boundary markers: Absent; there are no instructions to use delimiters or specific ignore-tags to separate user content from system instructions.
- Capability inventory: The skill itself provides no direct tools or executables, but it is intended for use with an agent that likely possesses file-system access capabilities.
- Sanitization: Absent; the skill does not define methods for sanitizing or filtering input code for security purposes, focusing instead on structural and semantic accessibility.
Audit Metadata