zendesk-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS] (SAFE): The skill documentation references a remote MCP endpoint (
https://rube.app/mcp). This is the standard method for registering tool-providing servers in Model Context Protocol environments and does not involve executing untrusted local scripts. - [PROMPT_INJECTION] (SAFE): No override markers, role-play injections, or instructions to ignore system guidelines were found in the skill body or metadata.
- [DATA_EXFILTRATION] (SAFE): The skill does not contain logic to access sensitive local files (e.g.,
.env, SSH keys) or hardcoded API keys. Authentication is managed through the referenced MCP connection tool. - [COMMAND_EXECUTION] (SAFE): There are no shell commands, subprocess calls, or system-level operations defined within the skill.
- [REMOTE_CODE_EXECUTION] (SAFE): No patterns of downloading and piping remote content to an interpreter (e.g.,
curl | bash) were detected.
Audit Metadata