artboard
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with the 'astria' CLI utility, which is a resource provided by the skill's author (astriaai). All operations are consistent with the stated purpose of managing image generation tasks.
- [COMMAND_EXECUTION]: The skill constructs shell commands to be executed via the 'astria' tool. This usage is restricted to the specific vendor toolset defined in the 'allowed-tools' configuration, ensuring the agent operates within a controlled environment.
- [DATA_EXPOSURE]: The skill handles model identifiers (FaceIDs) and image prompts relevant to the user's project. It does not attempt to access sensitive files, credentials, or personal information on the host system.
- [PROMPT_INJECTION]: The skill ingests user input regarding video themes and settings to populate image prompts. While this represents a surface for indirect prompt injection, the scope of the risk is limited to the visual content of the generated storyboard and does not pose a threat to the agent's core safety instructions or the underlying system.
Audit Metadata