Platform Capabilities
One install. Seven capabilities. Prompt-driven. CVE autopatch, PR review, CI hardening, guardrail review, audit packets, and more.
CVE/GHSA autopatch
Report a vulnerability. XOR writes the fix, adds a failing test, and opens a PR with CI passing. Cost range: $2.64 to $76.54 per fix.
PR code review
XOR reads the full diff, flags security risks and unsafe patterns, posts inline review comments with specific fix suggestions. Uncertainty stop: if confidence is low, XOR says so instead of guessing.
One install. Seven capabilities. Prompt-driven.
Every capability works the same way: mention @xor-hardener in a PR or issue comment, describe what you need, and XOR does the work. No configuration files. You can also use explicit commands — see the Command Reference.
CVE/GHSA autopatch
Report a vulnerability. XOR writes the fix, adds a failing test, and opens a PR with CI passing.
@xor-hardener Minimal autopatch for CVE-2024-1234.
Add a failing test. Keep CI green. Target the main branch.
Without XOR
20-45 min triage + 1-4 hours fix
With XOR
Under 15 min. PR with test included.
At $150/hr fully loaded cost, manual triage costs $75-$600 per CVE. XOR range: $2.64 to $76.54 — 8x to 227x cheaper.
PR code review
XOR reads the full diff, flags security risks and unsafe patterns, and posts inline review comments with specific fix suggestions. If confidence is low, XOR says so instead of guessing.
@xor-hardener /review
GitHub Actions hardening
Pins actions to SHA instead of tags and reduces workflow permissions to least-privilege per job. CI stays green. GitHub Actions supply chain attacks rose 350% in 2025 (StepSecurity).
@xor-hardener Pin actions by SHA and reduce workflow permissions per job. Keep CI green.
Guardrail review
When a PR deletes or refactors risky code, XOR reviews the change, flags what could go wrong, and stops when its confidence is low. No false positives from guessing.
PR audit packet
After CI passes, XOR compiles evidence: files changed, commit SHAs, tests added, CI job URLs, linked issues, reviewer sign-offs. One comment, everything an auditor needs. For 1,000 PRs per quarter, this saves 250-500 hours of audit prep.
Green-build autopatch
When a test fails in CI, XOR reads the failure log, diagnoses the root cause, and opens a PR with the smallest safe diff to restore a green build.
OSV dependency review
XOR reads an osv-scanner output, triages exploitable vs. noise vulnerabilities, and proposes minimal version bumps with PRs for safe updates.
[NEXT STEPS]
Go deeper
FAQ
How many capabilities does XOR have?
Seven: CVE/GHSA autopatch, PR code review, GitHub Actions hardening, guardrail review, PR audit packet, green-build autopatch (coming soon), and OSV dependency review (coming soon).
Do I need to memorize commands?
No. XOR reads natural language. Comment '@xor-hardener Review this PR for security issues' and XOR decides which capability applies. You can also use explicit commands like /review.
What is the economic impact of automated patching?
At $150/hr fully loaded engineering cost, each manually triaged CVE costs $75-$600. XOR's benchmark data shows $2.64 to $76.54 per automated fix — 8x to 227x cheaper than manual work.
Patch verification
XOR writes a verifier for each vulnerability, then tests agent-generated patches against it. If the fix passes, it ships. If not, the failure feeds back into the agent harness.
Automated vulnerability patching
AI agents generate fixes for known CVEs. XOR verifies each fix and feeds outcomes back into the agent harness so future patches improve.
Benchmark Results
62.7% pass rate. $2.64 per fix. Real data from 1,664 evaluations.
Benchmark Results
62.7% pass rate. $2.64 per fix. Real data from 1,664 evaluations.
Agent Cost Economics
Fix vulnerabilities for $2.64–$52 with agents. 100x cheaper than incident response. Real cost data.
Agent Configurations
13 agent-model configurations evaluated on real CVEs. Compare Claude Code, Codex, Gemini CLI, Cursor, and OpenCode.
Benchmark Methodology
How CVE-Agent-Bench evaluates 13 coding agents on 128 real vulnerabilities. Deterministic, reproducible, open methodology.
Agent Environment Security
AI agents run with real permissions. XOR verifies tool configurations, sandbox boundaries, and credential exposure.
Security Economics for Agentic Patching
Security economics for agentic patching. ROI models backed by verified pass/fail data and business-impact triage.
Validation Process
25 questions we ran against our own data before publishing. Challenges assumptions, explores implications, extends findings.
Cost Analysis
10 findings on what AI patching costs and whether it is worth buying. 1,664 evaluations analyzed.
Bug Complexity
128 vulnerabilities scored by difficulty. Floor = every agent fixes it. Ceiling = no agent can.
Agent Strategies
How different agents approach the same bug. Strategy matters as much as model capability.
Execution Metrics
Per-agent session data: turns, tool calls, tokens, and timing. See what happens inside an agent run.
Pricing Transparency
Every cost number has a source. Published pricing models, measurement methods, and provider rates.
Automated Vulnerability Patching and PR Review
Automated code review, fix generation, GitHub Actions hardening, safety checks, and learning feedback. One-click install on any GitHub repository.
Getting Started with XOR GitHub App
Install in 2 minutes. First result in 15. One-click GitHub App install, first auto-review walkthrough, and engineering KPI triad.
Dependabot Verification
Dependabot bumps versions. XOR verifies they're safe to merge. Reachability analysis, EPSS/KEV enrichment, and structured verdicts.
Compliance Evidence
Machine-readable evidence for every triaged vulnerability. VEX statements, verification reports, and audit trails produced automatically.
Compatibility and Prerequisites
Languages, build systems, CI platforms, and repository types supported by XOR. What you need to get started.
Command Reference
Every @xor-hardener command on one page. /review, /describe, /ask, /patch_i, /issue_spec, /issue_implement, and more.
Continuous Learning from Verified Agent Runs
A signed record of every agent run. See what the agent did, verify it independently, and feed the data back so agents improve.
Signed Compliance Evidence for AI Agents
A tamper-proof record of every AI agent action. Produces evidence for SOC 2, EU AI Act, PCI DSS, and more. Built on open standards so auditors verify independently.
Compliance Evidence and Standards Alignment
How XOR signed audit trails produce evidence for SOC 2, EU AI Act, PCI DSS, NIST, and other compliance frameworks.
Agentic Third-Party Risk
33% of enterprise software will be agentic by 2028. 40% of those projects will be canceled due to governance failures. A risk overview for CTOs.
MCP Server Security
17 attack types across 4 surfaces. 7.2% of 1,899 open-source MCP servers contain vulnerabilities. Technical deep-dive with defense controls.
How Agents Get Attacked
20% jailbreak success rate. 42 seconds average. 90% of successful attacks leak data. Threat landscape grounded in published research.
Governing AI Agents in the Enterprise
92% of AI vendors claim broad data usage rights. 17% commit to regulatory compliance. Governance frameworks from NIST, OWASP, EU CRA, and Stanford CodeX.
OWASP Top 10 for Agentic Applications
The OWASP Agentic Top 10 mapped to real-world attack data and XOR capabilities. A reference page for security teams.
See which agents produce fixes that work
128 CVEs. 13 agents. 1,664 evaluations. Agents learn from every run.