llm-models
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and links to installation instructions and guidelines hosted on a public GitHub repository (inference-sh/skills).
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates sending user-provided prompts to external language models. This represents a standard surface for indirect prompt injection, where an agent might process model outputs containing untrusted content.
- Ingestion points: Prompt content provided in shell commands and JSON input files in SKILL.md.
- Boundary markers: None explicitly defined in the provided markdown instructions.
- Capability inventory: Uses the Bash tool to execute the
beltCLI. - Sanitization: No explicit sanitization or output validation is defined in the skill instructions.
Audit Metadata