Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

sharp-edges — Claude Code skill: what it does, how to install

Audits API designs and configuration schemas for developer footguns. Flags dangerous defaults and fragile interfaces where the easiest path causes security vulnerabilities.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add trailofbits/skills --skill sharp-edges -a claude-code
Open on GitHub

What sharp-edges does

The skill targets ergonomic flaws in software interfaces rather than standard coding bugs. It inspects parameters that expose algorithm selection to untrusted input, identifies zero or empty defaults that silently disable checks, and flags functions accepting raw byte arrays instead of semantic types.

Under the hood, the autonomous sharp-edges-analyzer agent inspects code using Read, Grep, and Glob. It proceeds through four stages: surface discovery, edge-case probing, threat modeling, and finding validation.

Sharp edges intentionally skips business logic flaws and performance bottlenecks. It fails as a general-purpose linter because its strict focus is API usability and misuse resistance.

What it helps with

  • detect dangerous defaults in configuration schemas
  • spot insecure cryptographic algorithm parameters
  • evaluate API interfaces for misuse resistance
  • uncover silent validation failures in security checks

Example prompts for the agent

  • Review our authentication module using sharp-edges to find API footguns
  • Run sharp-edges analysis on the configuration schema for dangerous defaults
  • Audit this cryptographic helper interface with sharp-edges

How to install sharp-edges

1Skills CLI (Vercel)

npx skills add trailofbits/skills --skill sharp-edges -a claude-code

2Manually: put the files in place

~/.claude/skills/sharp-edges/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/sharp-edges/

From the same set35

The whole set →
semgrep trailofbits Runs a Semgrep static security audit on your codebase. It presents a plan for user confirmation and merges all findings into SARIF. Claude Code CX Codex Cursor +1 9,500installs differential-review trailofbits Reviews code changes for security issues using Git history and test coverage. Use it for commits, diffs, and pull requests that need a written review report. Claude Code CX Codex Cursor +1 8,800installs modern-python trailofbits Configures Python projects with a modern tooling stack: uv for dependency management, ruff for linting and formatting, ty for type checking. Use when starting new projects, writing scripts, or migrating from legacy tools. Claude Code CX Codex Cursor +1 8,700installs secure-workflow-guide trailofbits Guides smart contracts through Trail of Bits' 5-step security audit on check-in or before deployment. It runs static analysis, generates visual charts, and prepares fuzzing tests. Claude Code CX Codex Cursor +1 7,400installs agentic-actions-auditor trailofbits Inspects GitHub Actions workflows for prompt injection risks and insecure AI agent setups. Catches attacker inputs leaking into prompts via event contexts or environment variables. Claude Code CX Codex Cursor +1 6,700installs gh-cli trailofbits A skill that redirects GitHub requests from curl and fetch to authenticated gh CLI for repositories, pull requests, and issues. Use it for private repos and higher API limits. Claude Code CX Codex Cursor +1 6,600installs variant-analysis trailofbits Finds related occurrences of an already identified defect across a repository. Use it after a vulnerability or logic issue turns up and similar code needs checking. Claude Code CX Codex Cursor +1 6,400installs sarif-parsing trailofbits Processes existing SARIF reports from CodeQL, Semgrep, and other scanners. Use it to filter findings, remove duplicates, or prepare results for CI/CD. Claude Code CX Codex Cursor +1 5,900installs

Similar

labarchive-integration K-Dense-AI This skill guides work with LabArchives ELN API and Inventory API v1, including regional endpoints, request signing, and local request planning. Claude Code CX Codex Cursor +1 1,900installs pymatgen K-Dense-AI Analyzes, validates, converts, and transforms materials structures and computed data with pymatgen. Use it for phase diagrams, symmetry checks, electronic-structure files, and bounded Materials Project queries. Claude Code CX Codex Cursor +1 1,900installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs the-fool https://github.com/Jeffallan Challenges plans, architectures, and decisions using five structured reasoning modes. Useful for spotting blind spots and failure modes before writing code. Claude Code CX Codex Cursor +1 4,400installs security-review getsentry Finds injections, XSS, authorization flaws, and other vulnerabilities in code. Reports only high-confidence findings. Claude Code CX Codex Cursor +1 21,100installs git-guardrails-claude-code Matt Pocock This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes. Claude Code 499,069installs ponytail-review DietrichGebert ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits. Claude Code CX Codex Cursor +1 56,300installs ponytail-audit DietrichGebert It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. Claude Code CX Codex Cursor +1 44,800installs

Questions about sharp-edges

How do I install sharp-edges in Claude Code?

Run npx skills add trailofbits/skills --skill sharp-edges -a claude-code in your terminal.

What does sharp-edges do?

It evaluates APIs, configuration schemas, and libraries to ensure the secure path is the easiest path for developers. The skill flags designs that easily lead to misconfigurations or signature bypasses.

Can sharp-edges detect business logic bugs?

No, it is not built for business logic or routine code bugs. The analysis focuses entirely on interface ergonomics, dangerous options, and API misuse resistance.

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor