setup-agent
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
curl,grep,echo) to interact with the Karma API and manage local configuration files. - Evidence: Uses
curlto register agents and verify API keys athttps://gapapi.karmahq.xyz. - Evidence: Modifies shell configuration files (
.zshrc,.bashrc) to persist theKARMA_API_KEYenvironment variable, which is a standard persistence mechanism for developer tools. - [DATA_EXFILTRATION]: While the skill sends data (emails) to an external API, this is the primary purpose of the skill (authentication) and targets the vendor's official infrastructure.
- [CREDENTIALS_UNSAFE]: The skill handles API keys but follows security best practices by masking them in documentation and instructing the agent to ask for permission before saving them to disk.
Audit Metadata