rust-review

An agent skill by trailofbits, from trailofbits/skills. Tags: analysis, code-quality, debugging, developer-tools, security.

What it does

Performs comprehensive Rust security review for safe/unsafe boundary issues, memory safety in unsafe blocks, concurrency hazards, panic-induced DoS, FFI safety, and async runtime mistakes. Use when auditing Rust crates, services, or libraries — particularly those with `unsafe`, FFI, or concurrent code.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add trailofbits/skills --skill rust-review

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/trailofbits/skills
cp -r skills/plugins/rust-review/skills/rust-review ~/.claude/skills/rust-review

Safety box score

Grade C, moderate risk: 42 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a Rust-audit orchestrator that shells out through `uv run`, runs many subagents, and writes report artifacts in the workspace. The main risks are local code execution, broad file reads outside the repo during setup, and dependence on opaque helper scripts/prompts that are not all visible in this file.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	3 (high)	It repeatedly executes local commands and Python helpers, e.g. `uv run --no-project "${RUST_REVIEW_PLUGIN_ROOT}/scripts/build_run_plan.py"` and `generate_sarif.py`, so installing it grants shell/code execution in the user's environment.
Network access	0 (none)	This file does not specify any external downloads, API calls, or data exfiltration to remote hosts.
Filesystem reach	2 (moderate)	The root-resolution fallback reads outside the repo with `find ~/.claude ~/.codex . -path '*/plugins/rust-review/prompts/clusters/unsafe-boundary.md'`, and the workflow writes multiple artifacts under the working directory.
Secrets & credentials	0 (none)	It does not instruct the agent to read keychains, token files, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	1 (low)	It tells the user to install `uv` (`brew install uv` or the official installer), but it does not require sudo, global service registration, or shell/OS setting changes.
Instruction hijack surface	1 (low)	The skill contains a lot of prompt-orchestration text and references to subagent system prompts, but it does not tell the agent to ignore its rules, follow fetched instructions, or hide actions from the user.
Irreversible actions	2 (moderate)	It creates tasks, spawns workers and judges, sends messages, and can synthesize `REPORT.md` if a judge fails, so it performs substantial review workflow actions without additional human confirmation once invoked.
Transparency	2 (moderate)	Important behavior is delegated to unreadable helpers and prompts such as `${RUST_REVIEW_PLUGIN_ROOT}/scripts/*.py` and `agents/rust-review-{dedup,fp}-judge.md`, which are not included in the reviewed file set.

Before installing

Read the bundled helper scripts and agent prompts too: `scripts/build_run_plan.py`, `scripts/generate_sarif.py`, and `agents/rust-review-*.md`.
Run it in a throwaway clone or scratch workspace, since it writes `.rust-review-results/` and may inspect `~/.claude` / `~/.codex` while locating the plugin root.
Verify `uv` is installed and working before enabling the skill.
Make sure the repository and home directory do not contain sensitive files you would not want a review workflow to touch.

Rated 2026-10-21 by an automated review of 1 file from the skill's repository.

Source

Repository: trailofbits/skills (all skills from this repository)
Path: plugins/rust-review/skills/rust-review/SKILL.md
Branch: main
Collection: rust-review
Updated: 2026-09-19

c-review — Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities.
audit-context-building — Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere.
constant-time-analysis — Detects timing side-channel vulnerabilities in cryptographic code.
differential-review — Performs security-focused differential review of code changes.
dwarf-expert — Analyzes DWARF debug information in compiled binaries.
modern-cpp — Guides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ code, modernizing legacy patterns, or working on security-critical C++.