ai-automation-workflows

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references installation instructions hosted on a GitHub repository associated with the inference.sh service.
  • [COMMAND_EXECUTION]: The skill provides Bash and Python script templates that perform system operations, including CLI execution, file system management, and cron job scheduling for automation.
  • [PROMPT_INJECTION]: Example templates for data processing and conditional workflows ingest untrusted external data into LLM prompts, creating a surface for indirect prompt injection.
  • Ingestion points: Command-line arguments ($1) in conditional_workflow.sh and local file contents (cat $file) in data_processing.sh.
  • Boundary markers: The templates do not implement delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The scripts utilize the belt CLI, file system commands, and network utilities like curl.
  • Sanitization: There is no evidence of input validation or sanitization in the provided examples.
  • [DATA_EXFILTRATION]: A monitoring script example demonstrates how to send error logs to an external webhook URL using curl.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:35 PM
Security Audit — agent-trust-hub — ai-automation-workflows