fixing-accessibility
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are focused entirely on improving accessibility standards (ARIA, keyboard navigation, focus management) and provide safe code examples for remediation. No malicious behavior or high-risk patterns were identified.
- [PROMPT_INJECTION]: The skill processes external HTML files, creating a surface for indirect prompt injection.
- Ingestion points: Files specified via the
/fixing-accessibility <file>command. - Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions within the audited files.
- Capability inventory: The skill encourages the agent to review code and propose/apply concrete code-level fixes to the project.
- Sanitization: No validation or sanitization of the input HTML content is specified.
Audit Metadata