ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
beltCLI tool usingnpx skills add belt-sh/cliand recommends several utility skills from theinference-sh/skillsrepository. These resources originate from the service provider's infrastructure. - [COMMAND_EXECUTION]: The skill utilizes the
beltCLI via theBashtool to perform AI inference tasks, such asbelt app run google/veo-3-1-fast. This is the intended core functionality of the skill for generating social media assets. - [PROMPT_INJECTION]: The provided shell scripts interpolate user-defined variables like
$CONCEPTand$topicdirectly into model prompt strings. While standard for content generation, this represents a surface for indirect prompt injection if the source data is untrusted. - Ingestion points: Shell variables in the batch processing and repurposing templates in
SKILL.md. - Boundary markers: No explicit delimiters or instructions are used to separate user data from the system prompt in the examples.
- Capability inventory: The skill uses
Bashto interact with various generative models via thebeltCLI. - Sanitization: No input sanitization or validation is implemented in the provided shell templates.
Audit Metadata