wechat-article-formatter

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to prompt for and save WECHAT_APP_ID/WECHAT_APP_SECRET and shows embedding them into the token request URL/params, which requires the LLM to handle or output secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests user-supplied markdown content (including arbitrary free text) from a provided local file path (and possibly pasted content), then sends that markdown as the markdown field to the bm.md render API at runtime.