Offense Brings Security Tools to Coding Agents
Offense is an open-source security toolset that gives coding agents CLI, MCP, and HTTP access to dependency audits, source analysis, workflow checks, and remediation verification. Offense Research offers optional hosted execution alongside local and self-hosted modes.
Offense’s strongest idea is treating security as an evidence-and-verification workflow for coding agents, rather than another opaque autonomous scanner.
- –Audits npm and pnpm lockfiles against OSV and npm metadata through a local engine
- –Exposes the same security capabilities through CLI, MCP, and HTTP for agents including Codex and Claude Code
- –Runs Opengrep and Zizmor checks in isolated Docker containers for source and GitHub Actions analysis
- –Structured reports distinguish advisory matches from confirmed vulnerabilities and preserve coverage gaps
- –The current focus is narrower than a full AppSec platform, with local dependency analysis requiring Node.js 24+ and broader tools depending on deployment
DISCOVERED
13m ago
2026-11-10
PUBLISHED
1h ago
2026-11-10
RELEVANCE
AUTHOR
AniC_dev