gitai-automation
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on an external CLI tool (
@notyped/gitai). The instructions implement a robust security practice by explicitly prohibiting the AI agent from installing or configuring this package. This ensures that software installation and API key management remain under the direct control of the human user. - [COMMAND_EXECUTION]: The skill uses the
Run Commandtool to interact withgitai. It includes mandatory prerequisite checks (command -v gitaiand checking for the existence of~/.gitai) to ensure the environment is correctly set up by the user before attempting any operations. - [CREDENTIALS_UNSAFE]: While the skill involves the use of AI provider API keys, they are stored in a local configuration file (
~/.gitai) managed by the user. The instructions do not direct the agent to read, expose, or exfiltrate these credentials.
Audit Metadata