kuikly-network-and-json

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt's code examples embed credentials (e.g., "Authorization: Bearer token", "session_id=abc123", put("password","123456")) directly into headers/body, which encourages including secret values verbatim in outputs and is therefore a high-risk pattern.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflows (see "Workflow: HTTP Requests" and the NetworkModule API reference) explicitly instruct using networkModule.httpRequest / requestGet / requestPost to fetch arbitrary URLs and then parse and act on the returned JSON/binary data, meaning the agent will ingest untrusted third‑party web content that can influence its actions.