app-store-screenshots
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the vendor's official GitHub repository (
inference-sh/skills). This is standard procedure for tool setup. - [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool to interact with remote inference services (e.g.,belt app run). These commands are used to generate visual assets like mockups and preview videos based on user prompts. - [INDIRECT_PROMPT_INJECTION]: The skill defines an interface where user-provided prompts are interpolated into commands sent to generative models. While this presents an attack surface where a user might attempt to bypass model safety filters, the risk is localized to the generated media output and is managed by the remote model's own safety guardrails.
- [SAFE]: No malicious patterns such as obfuscation, credential exfiltration, persistence mechanisms, or privilege escalation were detected. The skill's behavior aligns with its documented purpose.
Audit Metadata