plugin-forge

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

• Third-party content exposure detected (high risk: 1.00). The skill's docs and workflows (SKILL.md and references/marketplace-schema.md and workflows.md) explicitly show adding marketplaces from GitHub or arbitrary URLs (e.g., /plugin marketplace add owner/repo and "source": {"source":"url"}), and installing plugins which load third‑party plugin files (commands, skills, agents, hooks) that the agent will read and can change tool use/behavior, so untrusted user-generated content can influence agent actions.