---
title: "TU compiler analyzer: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/trailofbits-3-tu-compiler-analyzer/
description: "Pins the zeroize-audit per-file compiler analyzer that stops without compile flags, refuses a finding that lacks the evidence it names, and deletes that unit's temporary artifacts."
---

# TU compiler analyzer: review, role & definition · Undominated.ai

> Pins the zeroize-audit per-file compiler analyzer that stops without compile flags, refuses a finding that lacks the evidence it names, and deletes that unit's temporary artifacts.

[← Explore all agents](/agents/)

SECURITY REVIEW / Trail of Bits

# TU compiler analyzer

Pins the zeroize-audit per-file compiler analyzer that stops without compile flags, refuses a finding that lacks the evidence it names, and deletes that unit's temporary artifacts.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/trailofbits/skills/tree/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 4 linked sources
 Publisher Trail of Bits
 Licence [CC-BY-SA-4.0 ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE)
 Revision 8e54050ae63c
 [Read what was—and wasn’t—checked ↓](#review)

“A per-file compiler analyzer that stops without compile flags, refuses a finding that lacks its required compiler evidence, and still deletes temporary artifacts.”

 [Trail of Bits · upstream description ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The agents index has no entry for plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md.
- The file stops when compile flags cannot be extracted, refuses an optimized-away or assembly finding without the evidence it names, and deletes that unit's temporary compiler artifacts even on partial failure.

### A good fit for

 - One translation unit whose compile-database flags and enable flags are already supplied by the zeroize-audit orchestrator

### Weigh up before choosing

 - This review did not execute the resource.
- A Markdown profile does not register a native subagent by itself.
- The install line adds the trailofbits/skills marketplace. It does not install the zeroize-audit plugin or this agent by itself.
- The file says assembly and semantic IR are skipped when IR emission fails because they depend on IR files. The assembly step's own command reads the source file. That is an inaccurate dependency note, not two opposing actions.
- The compile-commands and IR-analysis references were not opened. Cleanup of temporary artifacts was not run.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md
- plugins/zeroize-audit/README.md
- README.md
- LICENSE

### Our findings

 - If compile-flag extraction exits non-zero, the agent writes an error and stops. The error section also writes empty arrays and exits.
- An optimized-away wipe requires an IR diff. The file says never to emit that finding from source alone.
- Stack retention and register spill require assembly evidence. The file says never to emit either from source or IR alone.
- Assembly, semantic IR, and CFG each run only when their enable flag is true. Those three flags are inputs in the file's parameter table.
- Temporary compiler artifacts for that translation unit are removed even on partial failure. An IR emission failure writes an empty IR array, skips assembly and semantic IR, and can still continue to CFG.

### Not established by this review

 - The resource was not executed and its tools were not called.
- No translation unit or compile database was supplied.
- The referenced flag-stripping and IR-analysis notes were not opened, and the cleanup was not run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md)

DOCUMENTED COMMAND

 /plugin marketplace add trailofbits/skills Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The README's Claude Code section is that line, then /plugin menu to browse plugins.
- The same README names zeroize-audit as the plugin for missing or compiler-eliminated secret zeroization in C, C++, and Rust. The marketplace command does not install that plugin or this agent by itself.
- The Codex section uses codex plugin marketplace add trailofbits/skills and a placeholder plugin name, so that line is not install.command.

### Before you start

 - Claude Code or Codex marketplace support
- The orchestrator inputs named in the file, including one translation unit, its compile database, and the three enable flags

### Compatibility

Claude Code · Codex

### Implementation

c

### Single-file compiler pass that stops without flags and deletes its temporary artifacts

 - Read one translation unit and its compile-database entry
- Write that unit's compiler-analysis JSON
- Stop when compile flags cannot be extracted, and delete that unit's temporary compiler artifacts even after a partial failure

### Cost model

CC-BY-SA-4.0; no price is stated for this agent, and it was not run

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [3-tu-compiler-analyzer ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/agents/3-tu-compiler-analyzer.md Supports: stop without flags, evidence refusals, enable-flag skips, and cleanup on partial failure
- [zeroize-audit README ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/README.md) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/zeroize-audit/README.md Supports: this agent is the per-translation-unit C and C++ compiler pass
- [Repository README ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/README.md Supports: marketplace install line, Codex compatibility, and the zeroize-audit row
- [Repository LICENSE ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE) Checked 2026-10-14 https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/LICENSE Supports: Attribution-ShareAlike 4.0 International

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Adversarial modeler ↗ Pins Trail of Bits' differential-review agent that models high-risk changes and says not to run on low or medium risk diffs.](/agents/trailofbits-adversarial-modeler/)[### C review worker ↗ Pins the c-review producing worker that reads source, writes one part file, and states that it has no shell.](/agents/trailofbits-c-review-worker/)[### Crypto Analyzer ↗ Reviews cryptographic design and code for weak primitives and mishandled keys, and points exploitation elsewhere.](/agents/pentest-crypto-analyzer/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
