wjx-cli-use

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes and recommends passing API keys and passwords directly in commands (e.g., --api-key and an example --password pass123), which would require the agent/LLM to 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: 0.90). The skill's workflows explicitly query and ingest user-generated survey data from the Wenjuanxing (问卷星) API (e.g., wjx response query, wjx response download, wjx response report, wjx survey get / export-text), so the agent will read untrusted third-party content (survey responses/public webhook payloads) that could contain instructions and materially influence subsequent tool actions.