🛡️ AgentSentinel Safety Layer — 智能体安全护栏
v0.1.2本地优先的预算与策略护栏，实时拦截智能体越权或超预算行为，可同步至 AgentSentinel 云端，实现多智能体统一安全治理。
2· 2.8k·6 当前·6 累计
by @jimmystacks 安全扫描
OpenClaw
安全
medium confidenceThe skill's code, runtime instructions, and required credential are consistent with a local-first policy/budget guardrail that only uploads telemetry when an API key and explicit sync are used, though there are a few minor undeclared environment variables and privacy considerations to review before enabling cloud sync.
评估建议
This skill appears to do what it says: local checks and local budget tracking by default, with an explicit opt-in sync to AgentSentinel when you set AGENT_SENTINEL_API_KEY and run the sync command. Before enabling cloud sync, consider: 1) review callguard.yaml to ensure policies don't inadvertently capture sensitive commands; events include the command string and will be uploaded during sync; 2) AGENT_SENTINEL_AGENT_ID (optional) may be included in uploads — avoid setting it if you don't want an...详细分析 ▾
✓ 用途与能力
The name/description match the implementation: local policy and budget enforcement, local state and events, and an opt-in sync to https://api.agentsentinel.dev. Required runtime (python3) and primary credential (AGENT_SENTINEL_API_KEY) are appropriate for the claimed cloud-sync feature.
✓ 指令范围
Runtime instructions (bootstrap, check, status, reset, sync) operate only on workspace callguard.yaml and a per-user .agent-sentinel state/events files. The code does not execute the provided command string — it only checks it. Remote network activity is explicit (sync) and disclosed in SKILL.md.
✓ 安装机制
No install spec is provided (instruction-only skill) and the wrapper is pure Python using stdlib HTTP. No external downloads or package installs are performed by the skill bundle.
ℹ 凭证需求
PrimaryEnv AGENT_SENTINEL_API_KEY is declared and used only for sync. However, the code also reads AGENT_SENTINEL_HOME (to locate state/events) and AGENT_SENTINEL_AGENT_ID (included as agent_id in the uploaded payload) without those being declared in requires.env. Uploaded events include the command string and other details — enabling cloud sync will transmit that data to the platform.
✓ 持久化与权限
The skill writes only its own state and events under .agent-sentinel (or AGENT_SENTINEL_HOME) and may create callguard.yaml in the workspace via bootstrap. always:false and normal autonomous invocation are in effect; the skill does not modify other skills or system-wide configs.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv0.1.22026/2/1
AgentSentinel skill v0.1.2 - Added initial implementation files, including sentinel_wrapper.py and test_wrapper.py. - Introduced local-first budget and policy guardrails for agent actions. - Integrated command-line interface for policy checks, status reporting, sync, and session resets. - Provided optional remote sync to AgentSentinel cloud triggered by API key and explicit sync command. - Added documentation on usage, commands, configuration, security, and product scope.
● 无害
安装命令
点击复制官方npx clawhub@latest install agent-sentinel
镜像加速npx clawhub@latest install agent-sentinel --registry https://cn.longxiaskill.com