intlayer-content

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

• Third-party content exposure detected (high risk: 0.80). The skill's documentation and examples show it can fetch and ingest remote web content (e.g., externalContent: fetch("https://example.com") in references/concept_content.md and the Function Fetching / importMode: "fetch" / location: "remote" descriptions in SKILL.md), meaning untrusted third‑party content can be read and incorporated into dictionaries that the agent will interpret and render.