skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The scripts/package_skill.py and scripts/quick_validate.py are standard CLI utilities. They perform file reading and ZIP creation but do not execute arbitrary shell commands or user-provided strings.
  • REMOTE_CODE_EXECUTION (SAFE): The scripts/quick_validate.py script uses yaml.safe_load() to parse frontmatter. This is a secure practice that prevents the execution of arbitrary Python objects during YAML parsing.
  • DATA_EXFILTRATION (SAFE): No network operations (e.g., requests, curl, urllib) were detected in the scripts. The scripts only interact with the local filesystem for the purpose of packaging and validation.
  • PROMPT_INJECTION (SAFE): The documentation files (references/output-patterns.md and references/workflows.md) contain instructional templates for the agent. These are standard behavioral guidelines and do not contain instructions to bypass safety filters or ignore previous rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM