The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret output from cargo check and rustc. This represents an attack surface where malicious source code could generate specific error messages intended to manipulate the agent's behavior. However, the skill mitigates this by enforcing a rigid 'Compile-Fix Loop' and a strict 'Decision Tree'.
Ingestion points: The agent reads the diagnostic output from cargo check (described in SKILL.md and references/methods.md).
Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' prompts to wrap the compiler output.
Capability inventory: The skill uses cargo check, cargo fix, rustc --explain, and cargo clippy --fix (standard development tools).
Sanitization: No explicit sanitization or filtering of the compiler output is described.
[COMMAND_EXECUTION]: The skill utilizes standard, well-known Rust development tools such as cargo check, cargo fix, and rustc --explain to perform its primary function. These commands are executed locally within the project environment.
[EXTERNAL_DOWNLOADS]: The skill references the official Rust documentation (doc.rust-lang.org) for error explanations. These references target a well-known and trusted service for the Rust programming language.

rust-agents-compile-fix