Rust Safety Rules

The problem

The Rust compiler handles most safety checks, but it cannot verify the invariants inside unsafe blocks, the soundness of FFI wrappers, or hand-written Send and Sync implementations. These blind spots often lead to rare, hard-to-debug segfaults and undefined behavior in production.

What it does

• Enforces mandatory SAFETY comments for every unsafe block that explain the invariant being relied upon.
• Audits ownership patterns to identify when borrow checker struggles indicate a design flaw rather than a syntax error.
• Flags prohibited panics, unwraps, and expects in library code to prevent process crashes for callers.
• Verifies that unsafe functions include proper safety sections in doc comments for downstream callers.
• Reviews hand-written thread-safety claims (Send/Sync) and demands written proof of synchronization.

Frameworks & tools

Rust (2021 and 2024 editions), Cargo, thiserror, anyhow, and cargo-deny.

Why this beats prompting it yourself

Generic LLMs often suggest fixes that simply silence the compiler without addressing underlying soundness issues. This skill follows a strict "Trigger Matrix" to catch subtle signals like mutex guards crossing await points or missing raw pointer invariants that standard prompting misses.

Use cases

• Reviewing FFI wrappers to ensure C pointers are handled safely before dereferencing.
• Refactoring library code to replace panics with robust error handling using thiserror.
• Auditing thread-safety implementations in systems-level concurrency primitives.
• Cleaning up "reflexive cloning" and improper interior mutability patterns.

Known limitations

It cannot run cargo commands, Miri, or tests. It only reviews and edits code within the editor based on static analysis of the provided text.