osmatrix-setup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the NPM registry, a well-known service, to download and run the
osmatrixCLI tool vianpxwhen it is not present in the local environment. - [COMMAND_EXECUTION]: The skill executes local shell commands through the
osmatrixandgh(GitHub) CLI tools to manage guest lifecycles and submit compatibility reports to the vendor's GitHub repository. - [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection due to its processing of data from guest environments.
- Ingestion points: The agent reads external data from guest logs (e.g.,
C:\OEM\provision.log), status tool outputs, and screen captures. - Boundary markers: The skill relies on explicit instructions for the agent to review and confirm report contents with the user before transmission, rather than relying solely on automated boundaries.
- Capability inventory: The skill can execute shell commands, perform network operations via established CLI tools, and read/write its own configuration files.
- Sanitization: The instructions mandate that the agent must sanitize reports by removing sensitive information such as secrets, IP addresses, and user code before filing issues on GitHub.
Audit Metadata