yuque-personal-reading-digest

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly calls yuque_search and yuque_get_doc (see "Required MCP Tools" and "Step 2: Read the Document" in SKILL.md) to fetch and read Yuque documents (user-generated third-party content) and then uses that content to generate digests and decide follow-up actions like saving, so untrusted third-party content can influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). This skill calls yuque_get_doc at runtime to fetch a user-provided Yuque document URL (e.g., https://www.yuque.com/...) and injects that fetched document content into the model context to generate the digest, so the external URL directly controls agent prompts and is a required dependency.