nia

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to index and read external public sources (e.g., GitHub repos, docs.stripe.com, research papers) via tools like index/manage_resource/nia_read/nia_grep and to use WebFetch/WebSearch when needed, meaning the agent will ingest untrusted third‑party web content that can influence its subsequent actions.