The Agent Skills Directory

[SAFE]: The skill consists of instructional text and Rust code examples focused on ownership, lifetimes, error handling, and async programming. All provided code snippets are standard educational examples (e.g., using reqwest for HTTP requests to an example domain) and do not contain any hidden or malicious commands.
[PROMPT_INJECTION]: The instructions do not contain any attempts to override system prompts, bypass safety filters, or extract underlying instructions. The 'Trigger phrases' are standard keywords relevant to the Rust language.
[DATA_EXFILTRATION]: There are no patterns suggesting unauthorized data access or exfiltration. Mentions of sensitive file reading in code examples (std::fs::File::open(path)) are standard Rust API demonstrations and do not target specific sensitive paths like .ssh or .env files.
[EXTERNAL_DOWNLOADS]: The skill mentions external crates (e.g., thiserror, tokio, reqwest) in code examples, which are common and reputable libraries in the Rust ecosystem. There are no silent or piped package installations.
[INDIRECT_PROMPT_INJECTION]: As a coding assistant skill, it processes user-provided Rust code. While it lacks explicit boundary markers for untrusted input, the skill itself does not invoke any dangerous shell commands or file operations based on that input, adhering to its role as a language specialist.

rust-expert