table-schema

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill provides an optional Python script (scripts/run.py) to bootstrap the schema file. The script performs basic file I/O (reading and writing text files) using standard libraries and local helper functions. It does not spawn subprocesses or execute shell commands.
  • DATA_EXFILTRATION (SAFE): The skill documentation explicitly states 'Network: none'. The Python script confirms this by only interacting with the local file system using the provided --workspace path. No network libraries (e.g., requests, urllib) are used.
  • EXTERNAL_DOWNLOADS (SAFE): There are no external dependencies or remote scripts downloaded at runtime. All imports appear to be standard Python libraries or internal project utilities (e.g., tooling.common).
  • PROMPT_INJECTION (SAFE): The skill instructions in SKILL.md are purely structural and instructional. There are no attempts to bypass safety filters or override agent behavior in a malicious way. It uses standard instructional language.
  • DYNAMIC_EXECUTION (SAFE): The script generates a static markdown file based on templates. It does not use eval(), exec(), or any form of dynamic code generation or deserialization of untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM