agent-creator

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Comprehensive review of the skill's instructions and reference documentation found no indicators of malicious intent, prompt injection, or suspicious data handling.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run a Python validation script located in a sibling directory. This is a legitimate development workflow used to verify that generated agent files meet schema requirements.
  • [DATA_EXPOSURE]: The skill accesses the local file system to read templates and write agent configuration files to project-specific or user-home directories. These operations are restricted to the local environment and are necessary for the skill's stated purpose of managing agent definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:29 PM