unifi-access-support
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by implementing a 'review-first' workflow. It explicitly instructs the agent to display the sanitized JSON to the user and requires manual confirmation before any data is prepared for sharing.
- [EXTERNAL_DOWNLOADS]: The skill contains a reference to documentation on a GitHub repository belonging to the vendor (sirkirby/unifi-mcp). This is a legitimate reference to supporting documentation for the UniFi Access MCP integration.
- [DATA_EXFILTRATION]: The instructions strictly prohibit the skill from automatically posting, uploading, or submitting the collected data. It limits the agent's role to generating a local block of JSON or a file for the user to handle manually, effectively preventing automated exfiltration.
- [CREDENTIALS_UNSAFE]: The skill includes explicit warnings to the user to exclude credentials, logs, and private configuration from the support bundle, and it claims the underlying tool sanitizes sensitive identifiers automatically.
Audit Metadata