The Agent Skills Directory

[Prompt Injection] (SAFE): Analysis of the skill instructions found no attempts to override system prompts, bypass safety filters, or use adversarial role-play patterns.
[Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, private keys, or suspicious network exfiltration patterns were detected. The provided MQTT example uses a placeholder domain (broker.example.com) for instructional purposes.
[External Downloads & RCE] (SAFE): All referenced libraries (e.g., rumqttc, tokio, embassy) are standard components of the Rust ecosystem. There are no patterns involving the download and execution of untrusted remote scripts or arbitrary command execution.
[Obfuscation] (SAFE): The skill contains no encoded data, hidden characters (like zero-width spaces), or homoglyph-based evasion techniques. All content is clear-text and readable.

rust-iot