israeli-bituach-leumi

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, hardcoded credentials, or unauthorized data access patterns were detected. All external references target official Israeli government resources (btl.gov.il).
  • [COMMAND_EXECUTION]: The skill utilizes a local Python utility (scripts/calculate_benefits.py) to process benefit estimations. The script is self-contained and performs purely mathematical operations using standard libraries.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) related to its data processing workflow.
  • Ingestion points: The agent ingests user-provided parameters such as monthly salary, age, and employment history from the conversation to calculate benefits.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided data from the operational instructions provided to the agent.
  • Capability inventory: The skill uses the Bash(python:*) tool to execute the calculation script with user-derived arguments.
  • Sanitization: The skill lacks explicit instructions for the agent to sanitize or escape user input before interpolating it into the shell command string used to run the calculator.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 06:21 AM