gatewaystack-governance
由 davidcrowe 提供
Coding Agents & IDEs简介
Deny-by-default governance for every tool call — identity, scope, rate limiting, injection detection, audit.
描述
该技能的功能
Deny-by-default governance layer for OpenClaw that intercepts every tool call before execution. Runs five mandatory checks: identity verification, scope enforcement, rate limiting, prompt injection detection, and audit logging. Three optional features add output DLP, human escalation, and behavioral monitoring.
Because it hooks at the process level, the agent cannot route around it the way it could with in-prompt or middleware-based guardrails.
何时使用
- Blocking an agent from calling tools outside its approved scope
- Detecting prompt injection attempts before a tool executes
- Reviewing audit logs after an unexpected agent action
- Redacting PII from tool output before it reaches the agent
- Triggering human review when an agent tries a tool for the first time
示例工作流
User asks: why did the agent get blocked from calling the file_write tool?
- 1
Check append-only audit log at ~/.openclaw/plugins/gatewaystack-governance/audit.jsonl
- 2
Locate the denial record for the file_write invocation
- 3
Read the policy role assigned to the agent under the identity check
- 4
Confirm file_write is absent from the agent's tool allowlist in policy.json
- 5
Return the denial reason and the policy entry that caused it
Audit entry showing file_write was denied because the agent's policy role does not include it in the scope allowlist
前置要求
- @gatewaystack/transformabl-core npm package (only if output DLP is enabled)
- @gatewaystack/limitabl-core npm package (only if behavioral monitoring is enabled)
安装
clawhub install davidcrowe/gatewaystack-governance运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。