ai-social-media-content
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the 'belt' CLI and related skills from the author's official GitHub repository (inference-sh/skills).
- [COMMAND_EXECUTION]: Extensive use of the 'belt' CLI tool to run AI models via bash scripts. The execution is limited to the permitted 'belt' tool as defined in the skill's platform configuration.
- [PROMPT_INJECTION]: The skill interpolates user-defined variables such as '$CONCEPT' and '$topic' directly into AI prompts within SKILL.md. This ingestion point lacks explicit boundary markers or sanitization, creating a surface for indirect prompt injection, although the skill's capabilities are restricted to content generation tasks.
Audit Metadata