conda-install-agentjet-swarm-server

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

• Third-party content exposure detected (high risk: 0.80). The required workflow explicitly clones and installs code from public sources (e.g., "git clone https://github.com/modelscope/AgentJet.git" and pip installs including flash-attn from PyPI/GitHub/mirrors), so the agent would fetch and ingest untrusted third-party content that could materially influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs cloning and installing code from the remote repository https://github.com/modelscope/AgentJet.git during setup (git clone ... then pip install -e .), which fetches and executes external code at runtime and is required for the skill to work.