tauri-syntax-commands

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 examples (e.g., references/examples.md Example 4 "fetch_json" and the "download_file" pattern in SKILL.md) explicitly show commands that take arbitrary URLs and use reqwest::get to fetch and deserialize open-web content, meaning the agent would ingest and act on untrusted third-party data from arbitrary web sources.