fixing-accessibility-issues
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is strictly documentation-based and does not include any scripts, automated installation steps, or binary files.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it instructs the agent to process findings from external tools like axe-core and browser audits to generate code fixes. 1. Ingestion points: Audit reports, manual testing notes, and axe-core findings (SKILL.md). 2. Boundary markers: No explicit markers or 'ignore' instructions for the external content are defined. 3. Capability inventory: The agent is instructed to modify source files based on these findings. 4. Sanitization: No input sanitization or validation of the findings is specified.
- [SAFE]: All external links point to official W3C and WAI web standard documentation. The skill does not request or perform any network operations, credential access, or privileged system commands.
Audit Metadata