← Browse
unbound
websentry-ai ★ 0
Unbound enforces command policies, DLP guardrails, and jailbreak detection on Claude Code tool invocations while streaming session analytics to a security dashboard with zero-latency fail-open design. The plugin intercepts prompts and tool usage via hooks, checks against real-time policies, and logs all activity without disrupting the developer workflow.
Install
> /plugin marketplace add websentry-ai/claude-code-plugin
> /plugin install unbound
What it's made of
1 skill · 4 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 4 · PostToolUse, PreToolUse, Stop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- Unbound AI
- External tools
python3- Talks to
- nothing external detected
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 (websentry-ai).