init-onecli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read secret values from .env and to construct/run commands embedding those secrets (e.g., onecli secrets create --value <key>), and even to accept pasted tokens and include them in CLI commands, which requires the LLM to handle secret values verbatim.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). Flagged because the skill runs "curl -fsSL onecli.sh/install | sh" and "curl -fsSL onecli.sh/cli/install | sh" at runtime, which fetch and execute remote shell scripts from onecli.sh as a required installation step.