Security Agent
Turns GitHub Dependabot alerts into tracked findings, uses an AI triage model and a sandboxed analysis of the repository to decide whether each vulnerable dependency is actually reachable, opens remediation pull requests and tracks remediation deadlines with audit reports.
Find alternatives to Security Agent
What it does
- Code review
- Agentic coding
Features 7
- Dependabot syncContinuously brings GitHub Dependabot alert data into the configured repository scope.
- AI triageA dedicated model assesses advisory context and decides which findings need deeper investigation.
- Sandbox analysisRuns analysis against repository code to find usage locations, reachable paths, evidence and suggested fixes.
- Auto RemediationOpens remediation PRs automatically at a chosen severity threshold.
- Auto-dismissDismisses findings automatically when the analysis policy shows no action is needed.
- SLA trackingSets deadlines by severity and keeps approaching or breached findings visible.
- Audit reportsReports recorded Security Finding activity by period, repository, severity and state.
Sources
- Pricing
-
Official documentation · 11 Oct 2026
"AI triage, sandbox analysis, and remediation consume Kilo Code credits." No rate of its own and no free allowance are published; kilo.ai/pricing does not name Security Agent.
- Description
-
Official documentation · 11 Oct 2026
"identifies reachable risk, opens remediation PRs, sends deadline notifications, and preserves audit-ready activity history"; "Stage 1 AI triage"; "Stage 2 Sandbox analysis Inspect actual repository usage".
- What it does
-
Official documentation · 11 Oct 2026
Analyses repository code for reachable vulnerable paths and prepares fixes: "Automatically open remediation PRs at your chosen severity threshold".
- Sold within
-
Official documentation · 11 Oct 2026
Comes with a Kilo account: "Open Security Agent from your personal dashboard or an organization dashboard."; prerequisites are the GitHub App, Dependabot alerts and "Kilo Code credits for AI model usage", with no separate plan named.
- Name
-
Official documentation · 11 Oct 2026
"Security Agent turns GitHub Dependabot alerts into actionable Security Findings".
- URL
-
Official documentation · 11 Oct 2026
Kilo's own page, titled "Kilo - Security Agent: Find and Fix Dependency Risk"; listed under Coding Agents in the site menu.
- Deployment
-
Official documentation · 11 Oct 2026
Runs on Kilo's service against the selected GitHub repositories.
- Interfaces
-
Official documentation · 11 Oct 2026
Used from the web dashboard; "You can also open the audit report in the mobile app".
- Intended for
-
Official documentation · 11 Oct 2026
Security and engineering teams meeting remediation deadlines and audits.
Also from Kilo Code
-
Kilo Code AI agent
AI coding agent for VS Code, JetBrains IDEs, CLI and cloud platforms, with modes for coding, architecture planning, debugging and code review, access to 500+ models and zero AI-inference markup (bring-your-own-key supported).
-
Kilo Cloud Agents AI agent
Runs the Kilo coding agent in an isolated cloud Linux container started from a browser or phone: it clones the repository, works on its own branch and commits and pushes after every message, and can be started by webhook or on a schedule.
-
Kilo Code Reviewer Developer tool
Reviews pull requests on GitHub or GitLab (Bitbucket coming soon) and posts inline comments on bugs, security issues, performance and style, with a strictness setting and team instructions, and can also review uncommitted changes locally in VS Code or JetBrains.
-
Kilo Gateway API service
OpenAI-compatible inference API that routes requests to 500+ models from 60+ providers at provider rates, with bring-your-own-key support, per-request cost tracking and organization model and provider controls.
Open Kilo Code in the directory
Something wrong here? Send a correction — quote this product id: kilo-security-agent.