generic-max-supply
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions explicitly direct the agent to execute Python scripts, including 'scripts/model.py' and 'model_whatif.py', within the working directory. This workflow involves the execution of code that the agent has potentially modified.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes data from multiple CSV files which are used to influence the modification and subsequent execution of Python code.
- Ingestion points: Data is loaded from several CSV files in the 'scripts/data/' directory, including 'demand.csv', 'supply.csv', and 'processes.csv'.
- Boundary markers: The instructions do not define delimiters or markers to separate data from instructions within the processed files.
- Capability inventory: The agent is empowered to execute Python scripts ('python3 scripts/model.py') that it has been instructed to modify based on the input data.
- Sanitization: The 'data.py' script uses standard pandas loading without explicit validation or sanitization of the input data values before they are used in the model logic.
Audit Metadata