openclaw-setup
Warn
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill includes a troubleshooting command using
curlthat sends the user'sANTHROPIC_API_KEYwithin an HTTP header to theANTHROPIC_BASE_URL. If this URL is set to an untrusted endpoint (such as the hardcoded IP190.92.219.209provided in the example), the credentials will be exposed to that server. - [CREDENTIALS_UNSAFE]: The skill is specifically designed to manage and prompt for sensitive API keys (
ANTHROPIC_API_KEY) and store them in a local configuration file. - [COMMAND_EXECUTION]: The execution flow requires several shell commands, including environment variable checks (
echo), directory creation (mkdir), andopenclawCLI commands to list and status models. - [DATA_EXPOSURE]: The skill accesses the local file
~/.openclaw/openclaw.jsonto read and write configuration data, which includes plaintext API keys.
Audit Metadata