tooluniverse-custom-tool

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and references/python-tool.md) explicitly instructs JSON configs' fields.endpoint and example Python tools to call arbitrary HTTP endpoints via requests.get (e.g., "fields.endpoint" / "https://.../search"), meaning the agent will fetch and interpret untrusted third-party web/API content as part of normal tool execution which can influence subsequent actions.