Skip to content
ai101.tools
navigateopenescclose
Claude+372Whisper+228LangChain+168Codex+223NotebookLM+276DALL-E 3+192DeepL+249n8n+208Topaz Video AI+153LlamaIndex+161
secret-guard logo
Skill

secret-guard

Stops a write that carries a live credential.

0
SaveVisit website ↗

Install

Ships scripts
/plugin marketplace add DijitalPi/claude-plugins
/plugin install secret-guard@dijitalpi
Triggers on

Dosyaya yazma anında kendiliğinden çalışır; eşleşme bulursa yazmayı engeller

Author
DijitalPi
License
MIT

Every Write, Edit and NotebookEdit is scanned for credential shapes: AWS access key IDs, GitHub classic and fine-grained tokens, Anthropic and OpenAI keys, Google API keys, Slack tokens and webhooks, Stripe live keys, SendGrid keys, npm tokens and PEM private key blocks. A match blocks the write and reports only the first few characters. Generic password assignments are deliberately out of scope — they fire on fixtures and comments, and a guard that cries wolf gets switched off. Files in the .env family are skipped, since that is where a key belongs, and placeholder lines are read as documentation. Matching is local; nothing about the file leaves the machine.

Comments(0)

Sign in to comment

No comments yet — be the first.

Similar skills

Report this comment

Why are you reporting this?