mmx-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows and instructs passing API keys via a --api-key CLI flag (e.g., --api-key sk-xxxxx) and supports per-call keys, which encourages the agent to accept and emit secret values verbatim in generated commands—an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly documents the "mmx search query" command (web search via MiniMax) which fetches open/public search results that the agent is expected to read and may use to drive subsequent actions, exposing it to untrusted third-party content that could carry indirect prompt injections.