instagram-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and parse user-generated Instagram content (e.g., via instagram-cli inbox --output json and instagram-cli read <thread> in the "Typical Agent Workflow" and command docs), so untrusted third-party DMs could contain instructions that influence the agent's subsequent actions.