ai-automation-workflows

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The 'Data Processing Pipeline' section in SKILL.md demonstrates an indirect prompt injection surface by interpolating raw file content into an LLM prompt.
  • Ingestion points: The script reads all .txt files from the ./data/raw directory.
  • Boundary markers: Absent; the content of the files is directly appended to the prompt instruction without delimiters or guardrails.
  • Capability inventory: The skill uses belt app run to execute AI operations and shell redirection (>) to write outputs to the file system.
  • Sanitization: Absent; the raw output of cat $file is placed into the JSON input for the model.
  • [COMMAND_EXECUTION]: The skill provides extensive examples for executing shell commands, bash scripts, and Python scripts to orchestrate AI workflows using the belt CLI.
  • [EXTERNAL_DOWNLOADS]: The documentation references external installation scripts and additional skills hosted on the vendor's GitHub repository (github.com/inference-sh/skills).
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM
Security Audit — agent-trust-hub — ai-automation-workflows