1. Install
Use the projectβs documented installation path, then verify the installed version.
Installation instructions βSecurity hub
Start with a local repository check, review current evidence, then follow the security path that matches your task.
Threat DB v2.34.0Updated November 5, 2026
Local check
Install AgentSec and run its current alpha scanner locally. This website does not receive or inspect your files.
agentsec scan /path/to/repository --format json --redact 01 / Evidence
These values come from the bundled AgentSec feed and describe that database snapshot. They are not live measurements of the entire ecosystem.
02 / Local check
The scanner checks bounded repository inputs against bundled intelligence. A clean result is not proof of safety.
Use the projectβs documented installation path, then verify the installed version.
Installation instructions βExecute the scan inside the target repository. Review the exact files and evidence behind each finding.
Inspect AgentSec source βCurrent detectors do not cover every host-level persistence mechanism, Git-history witness, or runtime behavior.
03 / Paths
Each route answers one intent completely. The hub keeps orientation and current evidence without repeating every catalogue.
Understand how current attacks work, which ecosystems they affect, and which evidence supports each record.
Open this pathCheck whether a component is affected, inspect the primary source, and find the documented remediation.
Open this pathChoose an isolation boundary, understand what it excludes, and verify the controls before running an agent.
Open this pathReduce immediate risk, strengthen a workstation, and establish repeatable controls for a development team.
Open this path04 / Latest
Three recent feed events, ordered by their canonical date. Follow the source before making a time-sensitive decision.
Thomas Roccia published a gist of 73 GitHub repositories posing as Claude skills, Codex tools, MCP servers and OpenClaw projects. Each commits a ZIP that its README links; 51 were live at a 2026-11-04 re-check. Roccia reports that SKILL.md and settings files are clean and that two repositories store the ZIP under .claude. Per-row confidence differs and is preserved in the threat database.
The action checked out attacker-controlled PR head branches, read .mcp.json from the working directory and enabled all project MCP servers. A pull request carrying a malicious .mcp.json could run code on the Actions runner and expose workflow secrets when a privileged user triggered the action on that PR.
A completion/complete request without a ref field dereferenced nil and crashed the server before authentication, letting any client cause a denial of service.
05 / Checklist
Use this quick pass now. The full hardening route keeps the complete workstation and team checklist.
0 of 3 complete
The content remains available at a focused destination. These anchors preserve old bookmarks and inbound links.
Mechanisms, examples, campaigns, and mitigations.
Open threats βSearchable vulnerabilities, fixed-version status, and mitigations.
Open CVEs βDated event records and explicit detector coverage.
Open intelligence βTracked campaign records with reported dates and sources.
Open campaigns βFilter events, campaigns, authors, and malicious skills.
Search threats βProtection boundaries, silent failures, configuration, and runtime checks.
Configure sandbox βCapabilities and limits of the maintained scanner collection.
Compare tools βQuick checks, full audits, and the threat database terminal.
Open commands βDates describe the source record. Recheck the linked source before acting on time-sensitive risk information.