requirements

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching user-provided Feishu/PRD links using "lark-cli docs +fetch --doc" (and also accepts Figma links via /figma-prototype), meaning the agent ingests user-supplied third‑party documents and prototypes which it must read and use to drive subsequent actions and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to fetch a user-provided Feishu document link at runtime using "lark-cli docs +fetch --doc" (i.e., a Feishu document URL), and that fetched content is injected into the agent's context and used to generate and control subsequent prompts/documents, so it constitutes a runtime external dependency that can directly control agent instructions.