setup-architect

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

• Third-party content exposure detected (high risk: 0.90). The setup explicitly instructs cloning a public GitHub repo (git clone https://github.com/codenamev/ai-software-architect .architecture/.architecture) and copying/reading its agent documentation and templates (references/installation-procedures.md and Agent Documentation Setup), so the agent will ingest untrusted third‑party content that can alter agent workflows and behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The installation procedure explicitly runs git clone https://github.com/codenamev/ai-software-architect at runtime and copies the repository's agent documentation and templates (e.g., .architecture/agent_docs, AGENTS.md) into the project, which are then used to drive agent prompts/behavior — so the remote repo is a required runtime dependency that can directly control instructions.