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 belt CLI for interacting with various AI models. It proactively uses the allowed-tools frontmatter field to restrict its own environment, ensuring it can only execute shell commands starting with belt.
  • [EXTERNAL_DOWNLOADS]: The skill references installation guides and documentation hosted on the inference.sh and belt-sh GitHub repositories. These are well-known resources directly related to the skill's stated purpose of utilizing the inference.sh platform.
  • [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
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — ai-social-media-content