plugin-dev

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Test" step explicitly instructs adding a public GitHub plugin (claude plugin add https://github.com/v1truv1us/ai-eng-system), which causes the agent/platform to fetch and load arbitrary third‑party repository content (agents/commands/skills/hooks) that the system will read and that can change tool availability and behavior, enabling indirect prompt injection.