skill-creation-guide

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides utility scripts scripts/init_skill.py and scripts/package_skill.py that are intended to be executed by the agent or user. These scripts automate the lifecycle of skill development by creating folder structures and packaging files into ZIP archives (.skill files). Analysis of the source code confirms they perform legitimate file system operations without any malicious side effects.
  • [DYNAMIC_EXECUTION]: The init_skill.py script uses string templating to generate boilerplate code for new scripts. While this involves generating executable content, it is done locally within a controlled template system and does not involve executing arbitrary or untrusted code downloaded from external sources.
  • [EXTERNAL_DOWNLOADS]: No external network requests, downloads, or remote dependencies are utilized in the skill's instructions or scripts.
  • [DATA_EXFILTRATION]: The skill does not access sensitive system paths (like SSH keys or environment variables) and contains no mechanisms to transmit data over the network.
  • [PROMPT_INJECTION]: The instructions are meta-instructional, guiding the creation of other skills. They do not contain any directives aimed at overriding the agent's safety protocols or forcing restricted behaviors.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 03:24 AM