The Agent Skills Directory

[SAFE]: The skill provides detailed technical guidance on Rust development best practices, covering memory safety, error handling, and performance optimization.
[COMMAND_EXECUTION]: The skill instructs the agent to run standard Rust verification tools such as cargo fmt, cargo clippy, and cargo test. These commands are expected within the context of a code-focused development skill and target the local project environment.
[EXTERNAL_DOWNLOADS]: The skill references the installation of well-known and reputable Rust utilities, including cargo-flamegraph and cargo-insta, via the official Cargo package manager. These tools are standard in the Rust ecosystem for profiling and snapshot testing.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and processes external Rust source code and project files. However, the risk is inherent to its primary purpose as a development aid, and it relies on standard, established toolchains for analysis.
Ingestion points: The skill processes user-supplied Rust source code, diffs, and project configuration files defined as inputs in SKILL.md.
Boundary markers: The skill does not define specific boundary markers for demarcating untrusted code from instructions.
Capability inventory: The skill uses cargo for testing, linting, and formatting project files as described in the procedure of SKILL.md.
Sanitization: No explicit sanitization of the analyzed code is performed before invoking the Rust toolchain.

idiomatic-rust