data-profiler

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE] (SAFE): The skill analyzes DataFrames provided by the user. It does not attempt to access sensitive system paths (e.g., SSH keys, credentials) or environment variables.
  • [EXTERNAL_DOWNLOADS] (SAFE): No external code or data is downloaded from the internet. All logic is contained within the local script and standard dependencies.
  • [COMMAND_EXECUTION] (SAFE): Although 'Bash' is listed in the allowed-tools, the provided Python scripts do not use subprocess, os.system, or any other method to execute shell commands.
  • [REMOTE_CODE_EXECUTION] (SAFE): The skill does not use eval(), exec(), or any dynamic code loading mechanisms that could be exploited to run arbitrary code.
  • [PROMPT_INJECTION] (LOW): Like all tools that ingest external data (e.g., CSV files), there is a surface for indirect prompt injection if a user processes a malicious file. However, the skill only extracts statistical metrics (min, max, mean, etc.) and does not interpret the content of the data as instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:32 PM