product-changelog
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool to perform various operations, including account authentication (belt login) and running remote applications for image synthesis (falai/flux-dev-lora) and browser automation (infsh/agent-browser). These tools are used as intended for product documentation tasks. - [EXTERNAL_DOWNLOADS]: The skill references installation instructions hosted on the
inference-shGitHub repository and suggests the installation of supplementary skills via the platform's package manager. These references target the official repository of the service used by the skill. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied content (changelog descriptions) is interpolated into prompts for generative AI tools. While this represents a standard attack surface for data-to-tool transformations, the skill provides structured templates that help maintain formatting and safety.
Audit Metadata