BitsExplorer finds what people are building with AI, every day. See today's picks →

Agent Config Audit

Audit AI agent configuration for security risks: risky Claude Code permission rules and rules it silently skips, secrets and unpinned MCP servers in .mcp.json, exfiltrating hooks, plugin manifests, and prompt injection in CLAUDE.md, its @imports, AGENTS.md and .cursor rules. Table, JSON, Markdown…

Description excerpted from the original listing, which is linked below.

Open it Source code

Facts

Published: 4 Oct 2026 (26d ago)
Medium: web
Language: English (the page says so itself)
Subject: Developer tools
First seen: 28 Oct 2026, 11:27 UTC

Built with

Claude Code: confirmed
the agent's own trailer in the repository's commit history

What we can see

77 hygiene score

Certificate issued by YR1, 62 days remaining
Cookie attributes no cookies set
Credentials and payment does not ask for either
Strict transport security set
Served over HTTPS
Mail authentication neither published
No insecure resources
Redirects none
Security headers 0 of 5 set
Third-party origins 2
Transport security TLS 1.3

Observed 28 Oct 2026 by fetching the page as a browser would. This describes hygiene and transparency, not safety: a missing header does not make a site dangerous, and a complete set does not make it trustworthy.

Made this?

Show it on your own site or README. It links back to this page.

Get the badge

For a web page

<a href="https://bitsexplorer.com/i/5282250/agent-config-audit"><img src="https://bitsexplorer.com/badge/5282250.svg" alt="Featured on BitsExplorer" height="22"></a>

For a README (Markdown)

[![Featured on BitsExplorer](https://bitsexplorer.com/badge/5282250.svg)](https://bitsexplorer.com/i/5282250/agent-config-audit)

Changes we have seen

28 Oct 2026 first indexed

Agent Config Audit

More built with Claude Code

Today's picks

The week in AI-built software