differential-review
Performs security-focused differential review of code changes.
Examining code for the line that is wrong
What it does
Performs security-focused differential review of code changes. Adapts analysis depth to codebase size, uses git blame for context, calculates blast radius by counting callers, checks test coverage of modified code, and generates a markdown report.
Read more
Use when reviewing a PR, commit, or diff for security vulnerabilities, checking whether a change re-introduces a previously fixed bug, asking what else a change could break, or finding which modified code has no test covering it.
What it can touch
No script files in its folder
Its folder holds text, not programs. It changes how your AI works; it does not bring code of its own.
How we know
Listed the 7 files in the skill’s folder on GitHub; none is a script or program.
Lets your AI run any terminal command without asking, while the skill is in use
While the skill is working, Claude Code will not stop to ask before each terminal command. The permission ends when you send your next message.
How we know
SKILL.md line 1: “allowed-tools: Read Write Grep Glob Bash”. Read 2026-10-06, commit 82fe822.
SKILL.md, line 1 ↗No serious risk pattern found
Launch7’s automated check read all 7 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-06, commit 82fe822 by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to trailofbits/skills: 2026-10-02 (4 days before the scan).
Read automatically from the skill’s own files on GitHub on 6 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Supported. Upload it once in Claude’s settings. Works on every plan, including Free.
Its licence does not let Launch7 hand you a copy. On GitHub, open the repository, choose Code → Download ZIP, unzip it, and zip just the differential-review folder.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
Licence: proprietary or unstated, so Launch7 links to it rather than redistributing it.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
Worth knowing
- The CC-BY-SA-4.0 licence does not clearly permit redistribution, so Launch7 links to it rather than bundling it.
More from trailofbits
All from this publisher →- audit-prep-assistant
Prepares codebases for security review using Trail of Bits' checklist.