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

Security Guidance

Security review of agent-written code at three points: on edit, on stop, and at commit.

0
SaveVisit website ↗

Install

Official
Claude Code: /plugin marketplace add anthropics/claude-plugins-official → /plugin install security-guidance@claude-plugins-official
Triggers on

Ajanın ürettiği kod yazılırken ve commit edilmeden önce güvenlik denetimi istendiğinde

Needs tools
ReadGrepBash
Author
Anthropic

Rather than one scan at the end, this plugin places checks where mistakes are cheapest to fix. Pattern-based warnings fire while an edit is being written, a diff review runs when the session stops, and a commit reviewer looks for injection, XSS, SSRF, hardcoded secrets and around twenty-five other classes before anything is recorded. Catching a hardcoded key before the commit is a different job from finding it in history afterwards.

Comments(0)

Sign in to comment

No comments yet — be the first.

Similar skills

Report this comment

Why are you reporting this?