membrane
Membrane is a static-analysis security audit tool that scans Claude Code and Codex project configurations and enabled plugins for 28 common security risks across secrets, permissions, hooks, MCP servers, prompt injection, and marketplace integrity. It uses bash, jq, and regex patterns to detect plaintext credentials, permission misconfigurations (including schema-validation typos), hook injection patterns, and other configuration flaws, writing durable audit findings to disk with tamper detection and optional suppressions.
Install
Source: https://github.com/pulseai-labs/pulsestack/tree/HEAD/membrane
What it's made of
4 commands · 1 skill
- Commands
- 4
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (pulseai-labs).