01-scaffold-and-plan
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the Antonella Framework base template from a remote repository via
composer create-projectorgit clonefromgithub.com/antonella-framework/antonella-framework. - [COMMAND_EXECUTION]: The skill executes multiple shell commands on the host system to initialize the project, including:
composer create-projectfor template acquisition.git cloneas a fallback mechanism.php antonellafor project updates, namespace configuration, and component generation (e.g.,updateproject,namespace,make,cpt,add).- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to command injection through user-provided variables.
- Ingestion points: User input collected during the "Discovery Phase," specifically the
[plugin-slug],[PluginNamespace],[ControllerName], and[PostTypeName]. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to treat these inputs as untrusted data.
- Capability inventory: The agent has the capability to execute shell commands (
composer,php,git,cd). - Sanitization: Absent. There are no instructions to validate or sanitize the user-provided strings before they are interpolated into the shell commands in Phase 1, Phase 2, and Phase 3.
Audit Metadata