ai-automation-workflows
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The
data_processing.shtemplate demonstrates reading local files and interpolating their content directly into AI prompts. - Ingestion points: Reads files from
INPUT_DIR="./data/raw"inSKILL.md. - Boundary markers: No delimiters or instructions to ignore embedded content are used in the prompt template.
- Capability inventory: Uses the
belt app runcommand andBashexecution environment as defined inSKILL.md. - Sanitization: No escaping or validation of the ingested file content is performed before processing.
- [COMMAND_EXECUTION]: Provides several Bash script templates and instructions for setting up cron jobs to automate tasks. It uses standard shell utilities and the vendor's CLI tool.
- [EXTERNAL_DOWNLOADS]: References installation instructions and related skills hosted on the inference-sh GitHub repository.
Audit Metadata