alterlab-nmc-portfolio-curator

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md Agentic Protocol and Workflow explicitly require the agent to "search the web" and "review the user's existing online presence: LinkedIn, Behance, social profiles" and to benchmark exemplary public portfolios, which means it ingests untrusted, user-generated third‑party web content that can influence its decisions.