ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines and related content from the inference-sh and belt-sh GitHub repositories. These resources provide documentation and tools necessary for the skill's primary functionality.
- [COMMAND_EXECUTION]: Numerous Bash examples demonstrate how to use the belt CLI to run various AI models for image, video, and text generation. The skill assumes the presence of the belt tool to perform its intended tasks.
- [INDIRECT_PROMPT_INJECTION]: The batch content creation and repurposing workflows interpolate variable data directly into shell commands and AI prompts. While standard for templates, this pattern creates a surface for potential injection if the variables process untrusted input.
- Ingestion points: The
CONCEPTandTOPICSvariables defined in the Bash scripts within SKILL.md. - Boundary markers: No explicit delimiters or instructions are used to separate user-provided content from the command logic.
- Capability inventory: The skill uses the Bash tool to execute CLI commands that interact with external APIs.
- Sanitization: No validation or escaping is applied to the data before interpolation.
Audit Metadata