when-managing-multiple-repos-use-github-multi-repo

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow clones and reads repository contents (e.g., scripts/multi-repo.sh clone-all / clone <REPO_X> and then runs analysis/tasks over the code), so any outsider-authored text present in those repos (issues/PR bodies, wiki/discussion text, or other contributors’ files) can be ingested into the agent’s LLM context during analysis/remediation.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes "npx claude-flow@alpha swarm init" (and other npx claude-flow@alpha commands) which fetches and executes remote npm package code at runtime to control the agent swarm, making it a required external runtime dependency.