mobile-experience-report

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected. The skill's functionality aligns with its stated purpose of mobile layout diagnostics.
  • [DATA_EXPOSURE]: The skill accesses WordPress page content and structure using wordpress_get_page and wordpress_list_pages. This data is used locally for analysis, and no network operations to non-vendor domains were found.
  • [COMMAND_EXECUTION]: While the skill uses MCP tools to interact with the WordPress environment, these are scoped to administrative tasks (listing pages, creating duplicates) and do not involve arbitrary shell command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading page content from the WordPress site via wordpress_get_page. Although this presents a theoretical attack surface where a malicious page could attempt to influence the agent's report, the risk is mitigated by the skill's diagnostic nature and its 'duplicate-first' safety model for applying any fixes.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:28 PM
Security Audit — agent-trust-hub — mobile-experience-report