block-accessibility
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches external web pages for the purpose of accessibility analysis. It includes explicit security guidelines to only fetch user-provided URLs and to treat all remote content as untrusted input to prevent indirect exploitation.
- [PROMPT_INJECTION]: The skill incorporates safeguards against indirect prompt injection by instructing the agent to ignore embedded scripts and dynamic content within the pages it audits.
- [DATA_EXFILTRATION]: No patterns of unauthorized data transmission or credential harvesting were detected. The skill's operations are confined to analyzing public web pages and generating local reports.
- [COMMAND_EXECUTION]: The skill does not utilize any shell commands or subprocess execution. Its output is limited to text-based analysis and code-level remediation suggestions for the user to review.
- [SAFE]: The skill follows security best practices for tools that interact with external data and its behavior aligns perfectly with its stated purpose of accessibility auditing.
Audit Metadata