tzai-brand
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill employs a shell loop to discover and execute a local script named
tzai-imagefrom a set of standard installation directories. This engine is responsible for the actual image generation process. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to download a necessary dependency (
kedoupi/tzai-image-skill) using thenpxpackage runner. As this resource is provided by the same author (kedoupi), it is treated as a standard vendor-managed resource. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where user-provided input is passed to a shell command argument (
--prompt). - Ingestion points: The user-supplied
subjectvariable used in the shell execution snippet inSKILL.md. - Boundary markers: None are defined in the provided execution logic to separate command arguments from user content.
- Capability inventory: The skill can execute local scripts via
bashwith parameters. - Sanitization: No explicit sanitization or escaping mechanisms for the prompt input are documented in the skill instructions.
Audit Metadata