Analyzing AgentScope Library

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

• Third-party content exposure detected (high risk: 0.80). This skill instructs the agent to git clone and read a public GitHub repository (https://github.com/agentscope-ai/agentscope) and to view files in the repo (examples, docs, module source), which are untrusted user-provided third‑party contents the agent would parse and could carry indirect prompt-injection payloads.