contabo
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to install the
cntbCLI, configure authentication, and manage VPS instances. These operations are necessary for the skill's primary purpose of infrastructure automation. - [EXTERNAL_DOWNLOADS]: Fetches the official
cntbCLI binary from Contabo's GitHub repository (github.com/contabo/cntb). As Contabo is a well-known cloud service provider, this download is treated as a routine integration step. - [PRIVILEGE_ESCALATION]: The installation instructions for Linux and macOS use
sudoto move the downloaded binary into/usr/local/bin/. While this involves elevated permissions, it is a standard procedure for installing command-line tools system-wide. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined parameters that are subsequently interpolated into shell scripts and
jqfilters, creating a potential surface for command injection if the inputs are not properly sanitized by the executing environment. - Ingestion points: Variables such as
SERVER_NAMEandCONTABO_REGIONprovided in theSKILL.mdsetup step. - Boundary markers: None; variables are interpolated directly into shell strings.
- Capability inventory: The skill uses
curl,tar,mv,ssh, and thecntbCLI, providing significant system and network access. - Sanitization: No explicit validation or escaping of user input is implemented within the skill scripts before execution.
Audit Metadata