protect-secrets
Secrets firewall for tool calls: denies (or asks, per level) any Read/Edit/Write/Bash/Grep that would read, search, modify, or exfiltrate .env files, SSH keys, cloud credentials…
Plugin-Paket · von Karan Bansal
Überblick
protect-secrets ist ein Plugin-Paket für KI-Coding-Tools von Karan Bansal. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Die letzte erfasste Änderung war am 2026-10-26. Stand unseres Marktplatz-Durchlaufs vom 2026-10-27.
Secrets firewall for tool calls: denies (or asks, per level) any Read/Edit/Write/Bash/Grep that would read, search, modify, or exfiltrate .env files, SSH keys, cloud credentials, or keystores, with tiered safety levels tunable via HOOK_SAFETY_LEVEL.
Was es abfragt
- Wird als Plugin-Paket installiert
- Deklarierte Hooks: 1
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add karanb192/claude-code-hooks
/plugin install protect-secrets@claude-code-hooksWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz karanb192/claude-code-hooks (Quelle auf GitHub öffnen) | Gelistet | 1.1.2 | Forks (GitHub): 48 Sterne (GitHub): 563 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| claude-code-hooks | karanb192/claude-code-hooks | 563 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Hooks: 1
PreToolUse
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
PreToolUse and PostToolUse hooks that catch secrets leakage patterns: echoing env vars, reading secret files, tokens in URLs, and missing gitignore/permissions on sensitive files.
-
Block destructive commands and secret access
-
Mod (function hooks): masks secret values in tool results before the model reads them. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set…
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Secure environment variable management with Varlock for secrets, API keys, credentials, and sensitive configuration.
-
Local-by-default, no-telemetry hooks inspect user prompts, supported tool inputs, outputs, and changed files in every enabled Claude Code or Codex session to block or mask secret…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Keeps private infrastructure details out of public repositories. Ships the privacy-guard skill: session rules for what must never cross the public boundary, plus a per-repo…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Secure environment variable management with Varlock for secrets, API keys, credentials, and sensitive configuration.
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Scan your codebase for exposed secrets and API keys, generate .env templates from environment variable usage, validate .env files against .env.example, and rotate secrets. Keeps…
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Manage GPG-encrypted environment secrets from Claude Code - a secure alternative to plaintext .env files. Store, retrieve, share, and revoke secrets in `dotsecenv` vaults where…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Operational skill for installing, configuring, operating, and debugging CrowdSec (cscli, LAPI/CAPI, hub, bouncers, WAF/AppSec) across bare-metal, Docker, and Kubernetes.
-
Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Enterprise-grade auth, easy to implement. Add login, SSO, MFA, and access control to any app with framework-aware guidance.
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
-
Query the StackHawk platform API for security posture reporting, findings analysis, and app management. Guides agents through authentication, data retrieval, and result…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
Gelistet auf Community GitHub marketplaces (5)
-
PreToolUse and PostToolUse hooks that catch secrets leakage patterns: echoing env vars, reading secret files, tokens in URLs, and missing gitignore/permissions on sensitive files.
-
Block destructive commands and secret access
-
Mod (function hooks): masks secret values in tool results before the model reads them. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set…
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Local-by-default, no-telemetry hooks inspect user prompts, supported tool inputs, outputs, and changed files in every enabled Claude Code or Codex session to block or mask secret…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
GitHub Security canvas for Copilot. Review your session's changes for vulnerabilities and fix code scanning alerts.
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages…
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management…
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Gelistet auf Cursor: cursor/plugins (5)
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
Build apps, scripts, and automations with the TypeScript SDK.
Gelistet auf Docker MCP Catalog (5)
-
stackhawk com.stackhawk/stackhawk
An MCP server that provides interaction with StackHawk's security scanning platform.
-
Connects with the Beagle Security backend using a user token to manage applications, run automated security tests, track vulnerabilities across environments, and gain intelligence…
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
MCP server for terminal commands, file operations, and process management
-
MCP server for using Semgrep to scan code for security vulnerabilities.
Gelistet auf Official MCP Registry (5)
-
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
-
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
-
Local secret guardrails: scan code, git changes and MCP configs for API keys; redact text
-
env-secret-exposure-analyzer-mcp io.github.vola-trebla/env-secret-exposure-analyzer-mcp
Scans projects for secret exposure: leaked API keys, unprotected .env files, and secrets in logs.
-
Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks.
Gelistet auf PyPI (MCP servers) (5)
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
altr-mcp-server io.github.altrsoftware/altr-mcp-server
MCP server for ALTR data security: databases, tags, policies, classification, access, audits
-
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
-
e2b com.mcparmory/e2b
Create and manage secure sandboxes for running AI agent code
Gelistet auf npm registry (MCP servers) (5)
-
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 624 rules, 39 tools, CLI + doctor + host audit.
-
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
-
ai-agent-firewall com.fidacy/ai-agent-firewall
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.