wenyan-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's examples and commands explicitly show passing appSecret, api-key, tokens, and other secrets as command-line arguments (e.g., --appSecret, --api-key, --token), which would require the LLM to embed actual secret values verbatim in generated commands or code.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly allows reading content from arbitrary URLs (e.g., "wenyan publish -f https://example.com/article.md" and the "--file | -f | 从文件或 URL 读取内容" option) and then renders/publishes that content, so untrusted third‑party pages could influence the agent's publishing actions.