ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of the
beltCLI for interacting with various AI models. It proactively uses theallowed-toolsfrontmatter field to restrict its own environment, ensuring it can only execute shell commands starting withbelt. - [EXTERNAL_DOWNLOADS]: The skill references installation guides and documentation hosted on the
inference.shandbelt-shGitHub repositories. These are well-known resources directly related to the skill's stated purpose of utilizing theinference.shplatform. - [PROMPT_INJECTION]: No patterns were identified that attempt to override agent behavior, extract system prompts, or bypass safety filters.
- [DATA_EXFILTRATION]: The skill does not attempt to access sensitive local files or directories. It uses standard authentication workflows (e.g.,
belt login) for accessing the remote inference services.
Audit Metadata