ai-automation-workflows

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The "Data Processing Pipeline" template in SKILL.md identifies a vulnerability surface for indirect prompt injection by interpolating raw file content directly into an LLM prompt string.
  • Ingestion points: Reads local text files from ./data/raw/ via the cat command.
  • Boundary markers: The content is interpolated without delimiters or instructions to the model to ignore embedded commands.
  • Capability inventory: Uses the belt CLI tool to send the generated prompt to AI models for processing.
  • Sanitization: No escaping, validation, or sanitization is applied to the file content before it is placed in the command string.
  • [COMMAND_EXECUTION]: The skill provides numerous Bash and Python script templates that execute the belt CLI tool for authentication and application execution. It also includes instructions for users to set up cron jobs for task persistence and uses subprocess.run in Python to interface with the platform's CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 10:14 PM