惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Martin Fowler
Martin Fowler
J
Java Code Geeks
博客园 - 【当耐特】
宝玉的分享
宝玉的分享
腾讯CDC
D
DataBreaches.Net
Microsoft Azure Blog
Microsoft Azure Blog
Engineering at Meta
Engineering at Meta
V
V2EX
F
Fortinet All Blogs
MyScale Blog
MyScale Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
T
Tailwind CSS Blog
Jina AI
Jina AI
GbyAI
GbyAI
大猫的无限游戏
大猫的无限游戏
A
About on SuperTechFans
酷 壳 – CoolShell
酷 壳 – CoolShell
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
U
Unit 42
B
Blog
M
MIT News - Artificial intelligence
N
Netflix TechBlog - Medium

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
Limit hook CLI tool authority [AI] (#81065) · openclaw/op...
pgondhi987 · 2026-05-13 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -6,6 +6,7 @@ Docs: https://docs.openclaw.ai

66
77

### Fixes

88
9+

- Limit hook CLI tool authority [AI]. (#81065) Thanks @pgondhi987.

910

- Require admin scope for node device token management [AI]. (#81067) Thanks @pgondhi987.

1011

- Restrict chat sender allowlist matching [AI]. (#80898) Thanks @pgondhi987.

1112

- Sessions: redact persisted tool result detail metadata before writing transcripts so diagnostic secrets do not survive tool output redaction. (#80444) Thanks @nimbleenigma.

Original file line numberDiff line numberDiff line change

@@ -82,6 +82,7 @@ export function createCronPromptExecutor(params: {

8282

resolvedVerboseLevel: VerboseLevel;

8383

thinkLevel: ThinkLevel | undefined;

8484

timeoutMs: number;

85+

senderIsOwner: boolean;

8586

messageChannel: string | undefined;

8687

suppressExecNotifyOnExit: boolean;

8788

resolvedDelivery: {

@@ -177,7 +178,7 @@ export function createCronPromptExecutor(params: {

177178

onExecutionPhase: params.onExecutionPhase,

178179

bootstrapPromptWarningSignaturesSeen,

179180

bootstrapPromptWarningSignature,

180-

senderIsOwner: true,

181+

senderIsOwner: params.senderIsOwner,

181182

});

182183

bootstrapPromptWarningSignaturesSeen = resolveBootstrapWarningSignaturesSeen(

183184

result.meta?.systemPromptReport,

@@ -314,6 +315,7 @@ export async function executeCronRun(params: {

314315

) => void;

315316

thinkLevel: ThinkLevel | undefined;

316317

timeoutMs: number;

318+

senderIsOwner: boolean;

317319

suppressExecNotifyOnExit: boolean;

318320

runStartedAt?: number;

319321

}): Promise<CronExecutionResult> {

@@ -350,6 +352,7 @@ export async function executeCronRun(params: {

350352

abortReason: params.abortReason,

351353

onExecutionStarted: params.onExecutionStarted,

352354

onExecutionPhase: params.onExecutionPhase,

355+

senderIsOwner: params.senderIsOwner,

353356

});

354357
355358

const runStartedAt = params.runStartedAt ?? Date.now();

Original file line numberDiff line numberDiff line change

@@ -319,6 +319,7 @@ describe("runCronIsolatedAgentTurn message tool policy", () => {

319319

resolvedVerboseLevel: "off",

320320

thinkLevel: undefined,

321321

timeoutMs: 60_000,

322+

senderIsOwner: true,

322323

messageChannel: "messagechat",

323324

suppressExecNotifyOnExit: true,

324325

toolPolicy: {

Original file line numberDiff line numberDiff line change

@@ -121,9 +121,40 @@ describe("runCronIsolatedAgentTurn isolated session identity", () => {

121121

const runRequest = requireFirstMockArg(runCliAgentMock, "runCliAgentMock") as {

122122

sessionId?: string;

123123

sessionKey?: string;

124+

senderIsOwner?: boolean;

124125

};

125126

expect(runRequest.sessionId).toBe("isolated-cli-run-1");

126127

expect(runRequest.sessionKey).toBe("agent:default:cron:cli-monitor:run:isolated-cli-run-1");

127128

expect(runRequest.sessionKey).not.toBe("agent:default:cron:cli-monitor");

129+

expect(runRequest.senderIsOwner).toBe(true);

130+

});

131+
132+

it("runs externally sourced CLI hook turns without owner tool authority", async () => {

133+

isCliProviderMock.mockReturnValue(true);

134+

mockRunCronFallbackPassthrough();

135+

runCliAgentMock.mockResolvedValue({

136+

payloads: [{ text: "done" }],

137+

meta: { agentMeta: { usage: { input: 10, output: 20 } } },

138+

});

139+
140+

const result = await runCronIsolatedAgentTurn(

141+

makeIsolatedAgentTurnParams({

142+

sessionKey: "hook:webhook:cli-monitor",

143+

job: makeIsolatedAgentTurnJob({

144+

payload: {

145+

kind: "agentTurn",

146+

message: "test",

147+

externalContentSource: "webhook",

148+

},

149+

}),

150+

}),

151+

);

152+
153+

expect(result.status).toBe("ok");

154+

expect(runCliAgentMock).toHaveBeenCalledOnce();

155+

const runRequest = requireFirstMockArg(runCliAgentMock, "runCliAgentMock") as {

156+

senderIsOwner?: boolean;

157+

};

158+

expect(runRequest.senderIsOwner).toBe(false);

128159

});

129160

});

Original file line numberDiff line numberDiff line change

@@ -462,6 +462,7 @@ type PreparedCronRunContext = {

462462

resolvedDelivery: ResolvedCronDeliveryTarget;

463463

deliveryRequested: boolean;

464464

suppressExecNotifyOnExit: boolean;

465+

senderIsOwner: boolean;

465466

toolPolicy: ReturnType<typeof resolveCronToolPolicy>;

466467

skillsSnapshot: SkillSnapshot;

467468

liveSelection: CronLiveSelection;

@@ -792,6 +793,7 @@ async function prepareCronRunContext(params: {

792793

resolvedDelivery,

793794

deliveryRequested,

794795

suppressExecNotifyOnExit: deliveryPlan.mode === "none",

796+

senderIsOwner: !isExternalHook,

795797

toolPolicy,

796798

skillsSnapshot,

797799

liveSelection,

@@ -1145,6 +1147,7 @@ export async function runCronIsolatedAgentTurn(params: {

11451147

thinkLevel: prepared.context.thinkLevel,

11461148

timeoutMs: prepared.context.timeoutMs,

11471149

suppressExecNotifyOnExit: prepared.context.suppressExecNotifyOnExit,

1150+

senderIsOwner: prepared.context.senderIsOwner,

11481151

});

11491152

if (isAborted()) {

11501153

return prepared.context.withRunSession({