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

sarif-parsing — Claude Code skill: what it does, how to install

Processes existing SARIF reports from CodeQL, Semgrep, and other scanners. Use it to filter findings, remove duplicates, or prepare results for CI/CD.

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

What sarif-parsing does

This skill works with SARIF output already produced by CodeQL, Semgrep, or other static analysis scanners. It can filter findings, deduplicate alerts, extract vulnerability details, convert report data, and prepare it for CI/CD use.

It follows the SARIF 2.1.0 structure, including analysis runs, rules, results, file locations, and finding fingerprints. Severity can come from a result or its matched rule. This matters for CodeQL: relying on result.level alone can miss errors whose level is stored in the rule configuration.

For one-off inspection, the skill covers jq queries. Python scripts can use pysarif. You need an existing SARIF file because this skill processes scan output rather than running scans.

What it helps with

  • read scan findings from a SARIF file
  • combine results from several scanners
  • remove duplicate security alerts
  • filter findings by resolved severity
  • extract rule IDs, file paths, and line numbers

Example prompts for the agent

  • Parse `results.sarif` and list findings resolved as `error`.
  • Aggregate these SARIF reports and deduplicate matching findings by fingerprint.
  • Extract rule IDs, messages, file paths, and lines from `results.sarif`.

How to install sarif-parsing

1Skills CLI (Vercel)

npx skills add trailofbits/skills --skill sarif-parsing -a claude-code

2Manually: put the files in place

~/.claude/skills/sarif-parsing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/sarif-parsing/

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 sharp-edges trailofbits Audits API designs and configuration schemas for developer footguns. Flags dangerous defaults and fragile interfaces where the easiest path causes security vulnerabilities. Claude Code CX Codex Cursor +1 6,900installs 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

Similar

ads-server-side-tracking AgriciDaniel Audits server-side paid-media measurement: verifies event parameters between browser and server, checks deduplication, data hashing, and privacy compliance. Spots conversion loss and bugs in sGTM, Meta CAPI, TikTok Events API. Claude Code CX Codex Cursor +1 3,300installs V3 Security Overhaul ruvnet A skill that runs a security pass over claude-flow v3: three critical CVEs closed, and secure-by-default patterns wired into the code. Claude Code CX Codex Cursor +1 1,100installs V3 Swarm Coordination ruvnet Orchestrates a 15-agent hierarchical mesh swarm to implement claude-flow v3. Manages parallel execution across security, core, and integration domains over a 14-week plan. Claude Code CX Codex Cursor +1 1,100installs use-link-identity stripe Tells the agent how to fetch a Link Agent Attestation Token or signed claims and send them to a service that asked for them. Claude Code CX Codex Cursor +1 9,200installs 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 security-audit cloudflare Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. Claude Code CX Codex Cursor +1 52,200installs

Questions about sarif-parsing

How do I install sarif-parsing in Claude Code?

In Claude Code, run npx skills add trailofbits/skills --skill sarif-parsing -a claude-code, then run npx skills add trailofbits/skills --skill sarif-parsing -a claude-code again.

What does sarif-parsing do?

It processes existing SARIF reports by filtering and grouping findings, removing duplicates, and converting data for CI/CD. It does not run CodeQL, Semgrep, or other scanners.

Why does CodeQL need severity resolution from rules?

A CodeQL result can omit result.level while its rule stores the severity in defaultConfiguration.level. The skill resolves the level from the rule when needed.

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