replay-ux-research
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established Sentry MCP tools to retrieve and analyze session replay metadata. No unauthorized network requests, credential harvesting, or remote code execution patterns were found.
- [DATA_EXFILTRATION]: The skill explicitly instructs the agent to protect user privacy by only using email domains and never including full email addresses in the output. It filters out internal Sentry employee data and focuses on telemetry available through official APIs.
- [COMMAND_EXECUTION]: The skill does not execute arbitrary shell commands or use dynamic context injection (!
command). All operations are performed within the scope of the Sentry MCP tools. - [EXTERNAL_DOWNLOADS]: No external scripts or packages are downloaded or executed. All logic is contained within the provided Markdown and reference files.
Audit Metadata