tam-sam-som-calculator
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): No instructions were found that attempt to override system prompts, bypass safety filters, or redirect agent behavior. The templates and examples are strictly focused on market analysis structure.
- DATA_EXFILTRATION (SAFE): The script
scripts/market-sizing.pydoes not access sensitive local file paths or perform network operations. It only processes inputs provided via command-line arguments. - COMMAND_EXECUTION (SAFE): The script performs basic mathematical calculations and string formatting. There is no usage of shell-executing functions such as
os.system,subprocess.run, oreval. - REMOTE_CODE_EXECUTION (SAFE): The skill is entirely self-contained. It does not download external scripts or list any external Python or Node.js dependencies.
- INDIRECT_PROMPT_INJECTION (INFO): The script accepts a
--currencyargument which is interpolated into the Markdown output. While this constitutes a data ingestion surface (Category 8), the capability is limited to console output and does not influence the agent's logic or environment safety. 1. Ingestion:scripts/market-sizing.pyviaargparse. 2. Boundary markers: Absent. 3. Capability inventory:print()to stdout only. 4. Sanitization: Numeric values are validated as floats.
Audit Metadata