auditing-pre-release-security

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

• Third-party content exposure detected (high risk: 1.00). Yes — the skill instructs the agent to run dependency installs and then inspect installed packages (e.g., "yarn install" and scanning /package.json and node_modules), which pulls and reads untrusted third‑party code from public package registries (npm/Yarn) as part of its workflow.