techartist-workflow

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md startup protocol (step 3, "Research task requirements") explicitly instructs the agent to use MCP tools like WebSearch and Fetch (and Vision MCP) to retrieve and read web references and visual material from the open web, which the agent must interpret to create implementation plans and drive actions—exposing it to untrusted third‑party content that could contain injected instructions.