ai-social-media-content

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'belt-sh/cli' and additional skills from the 'inference-sh' organization using the 'npx skills add' command. These resources are part of the core infrastructure required for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill uses the 'Bash(belt *)' tool to execute shell commands. It includes several examples of batch processing and automation using shell loops and variable interpolation.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-defined shell variables (e.g., '$CONCEPT', '$topic') directly into CLI commands and AI prompts. * Ingestion points: Shell variables and array elements defined in 'SKILL.md' (e.g., 'CONCEPT', 'TOPICS'). * Boundary markers: Absent; inputs are wrapped in standard double quotes without specific delimiter instructions for the LLM. * Capability inventory: Access to the 'Bash' tool restricted to the 'belt' command. * Sanitization: No explicit sanitization or escaping of user-provided content before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 10:16 AM