Differential Security Review is a Trail of Bits skill for reviewing a code change on its own, with its history. It classifies each changed file by risk (auth, crypto, external calls and value transfer rank high), scales its depth to codebase size, uses git blame on removed security code to catch reintroduced bugs, counts callers to estimate blast radius, and checks whether modified code has any test.
Every review ends with a markdown report file. Detailed methodology, attacker modeling, reporting templates and a vulnerability pattern list sit in companion files, and an adversarial-modeler agent can build exploit scenarios for high-risk changes.
What You Get
- A markdown report file with findings tied to line numbers, commits and concrete attack scenarios
- A risk level per changed file, from high to low, with stated triggers
- Blast radius numbers based on counted callers
- Flags for modified code that no test covers, with severity raised accordingly
Common Use Cases
- Reviewing a pull request that touches authentication or crypto
- Checking whether a change removes code added by an earlier security fix
- Asking what else a change could break across its callers
- Finding which modified lines have no covering test
What Makes It Unique
It reviews the diff in the context of history. It requires git blame on removed security code, treats refactors as high risk until shown otherwise, and refuses to judge risk by pull request size, since a two-line change can matter. It also requires stating coverage limits and confidence, and writing the report to a file.
Under The Hood
The skill loads one instruction file and, as needed, four companion documents and an agent definition. The agent uses Read, Write, Grep, Glob and Bash on your repository: git commands for diffs, history and blame, searches to count callers, and a write of the report file. It does not fetch web pages or call outside APIs by itself. Delegating to the adversarial-modeler agent starts a sub-agent that reads the same code.