Skills
Navigate
skills/inference-sh/skills/ai-social-media-content/Gen Agent Trust Hub

ai-social-media-content

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt command-line tool to perform operations like authentication and running AI model apps. Access is explicitly limited to the belt command via the allowed-tools frontmatter configuration.
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation hosted on the vendor's official GitHub repository (inference-sh/skills). These references are used for initial environment setup.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: User-defined text prompts are passed to various AI models (Claude, FLUX, Veo) via the belt app run command within the SKILL.md examples.
  • Boundary markers: None explicitly defined in the example workflows.
  • Capability inventory: Execution capability is restricted to the belt CLI tool as defined in the skill's manifest.
  • Sanitization: Content filtering and safety guardrails are implemented by the target AI models and the vendor's platform APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:38 PM
Security Audit — agent-trust-hub — ai-social-media-content