opper-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows and instructs using commands that embed API keys directly (e.g., opper config add default <your-api-key>, model creation with my-api-key), which would require the agent to include secret values verbatim in generated commands—an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These links point to a GitHub repository/releases (opper-ai/oppercli) and an Azure OpenAI endpoint; while GitHub and Azure are legitimate platforms, the prompt instructs directly downloading and executing an unsigned binary from a third‑party repo—an action that can distribute malware if the repo or binary are not independently verified—so treat it as potentially risky until you confirm the publisher, signatures/checksums, and repository reputation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The prompt's installation instructions explicitly include sudo commands that write to /usr/local/bin and change permissions, which direct performing privileged system modifications that can compromise the machine state.