duvo-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill documentation includes explicit examples of passing an API key on the command line (duvo login --api-key ) and references credential handling (secrets/DUVO_API_KEY), which could lead an agent to request and verbatim-embed user API keys or passwords in generated commands or code.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow of this Duvo CLI skill, outsider-authored free text can be ingested when users run commands like duvo cases create --from-file - / duvo cases update --data <text> or stream/poll run content via duvo runs start --message <text> / duvo runs messages <id> --follow --json, which forwards that arbitrary text into Duvo-hosted agent execution and message history.