parallel

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly includes web-search and URL-extraction endpoints (e.g., /v1beta/search and /v1beta/extract) that fetch and return content from arbitrary public web pages/URLs, which the agent is expected to read and use in its research/workflow, exposing it to untrusted third-party content that could contain injected instructions.