oh-xts-build-run
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied parameters that are passed into a command execution context.
- Ingestion points: The
--packageand--apiparameters defined inSKILL.mdtake input from the user. - Boundary markers: There are no explicit delimiters or instructions defined in the skill to treat these inputs as untrusted data or to prevent them from interfering with the underlying shell commands.
- Capability inventory: The skill invokes build and run logic, specifically utilizing the
hvigorwbuild tool and test runners mentioned in the implementation paths (e.g.,packages/cli/src/modules/xts/build-runner.ts). - Sanitization: The instructions do not specify any validation, escaping, or filtering for the parameters before they are used in the workflow.
- [COMMAND_EXECUTION]: The skill's primary purpose is to execute commands for the OpenHarmony build system and XTS testing environment. While these are necessary for the tool's functionality, they provide the capability for system interaction that can be targeted by input injection.
Audit Metadata