ai-social-media-content

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to interact with AI models. Access is appropriately restricted via the allowed-tools configuration to only allow commands starting with belt.
  • [EXTERNAL_DOWNLOADS]: The documentation points to the official vendor repository on GitHub and the npm registry for installing necessary CLI tools. These sources are consistent with the skill's stated purpose and author.
  • [PROMPT_INJECTION]: The skill processes user-defined strings (e.g., $CONCEPT, $topic) by interpolating them into prompts for AI models. This is a standard mechanism for content generation skills.
  • Ingestion points: Variable interpolation in bash scripts within SKILL.md.
  • Boundary markers: None used for interpolated variables.
  • Capability inventory: Execution of AI applications via the belt CLI.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:35 AM
Security Audit — agent-trust-hub — ai-social-media-content