laravel-ai-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and rule files (e.g., rules/tool-provider.md and SKILL.md) explicitly enable provider WebSearch/WebFetch and Document::fromUrl/FileSearch usage that fetch and ingest public web pages and arbitrary URLs as part of agent workflows, allowing untrusted third‑party content to be read and influence agent decisions.