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

A
About on SuperTechFans
C
Cybersecurity and Infrastructure Security Agency CISA
N
News and Events Feed by Topic
C
Cisco Blogs
Cisco Talos Blog
Cisco Talos Blog
A
Arctic Wolf
Scott Helme
Scott Helme
P
Palo Alto Networks Blog
S
Schneier on Security
D
Darknet – Hacking Tools, Hacker News & Cyber Security
T
Tor Project blog
量子位
G
Google Developers Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
B
Blog RSS Feed
NISL@THU
NISL@THU
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
AWS News Blog
AWS News Blog
爱范儿
爱范儿
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
L
LINUX DO - 最新话题
Security Archives - TechRepublic
Security Archives - TechRepublic
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
S
Secure Thoughts
Cloudbric
Cloudbric
aimingoo的专栏
aimingoo的专栏
L
Lohrmann on Cybersecurity
TaoSecurity Blog
TaoSecurity Blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Hacker News: Ask HN
Hacker News: Ask HN
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
The GitHub Blog
The GitHub Blog
有赞技术团队
有赞技术团队
S
Security @ Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
C
Cyber Attacks, Cyber Crime and Cyber Security
G
GRAHAM CLULEY
P
Proofpoint News Feed
V
V2EX
Martin Fowler
Martin Fowler
C
CERT Recently Published Vulnerability Notes
Attack and Defense Labs
Attack and Defense Labs
C
CXSECURITY Database RSS Feed - CXSecurity.com
The Cloudflare Blog
SecWiki News
SecWiki News
罗磊的独立博客
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
小众软件
小众软件
The Last Watchdog
The Last Watchdog

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 test: trim doctor command hotspots · openclaw/openclaw@c66f16a test: isolate agent auth and spawn hotspots · openclaw/openclaw@9285935 test: stabilize MCP startup disposal race · openclaw/openclaw@dd9d2eb test: merge browser contract server suites · openclaw/openclaw@5817a76 test: narrow ollama provider discovery setup · openclaw/openclaw@a0d9598 build: declare qa-lab aimock runtime dependency · openclaw/openclaw@24431e5 test: speed up safe-bins exec harness · openclaw/openclaw@ee856ab test: preserve tool helpers in embedded runner mocks · openclaw/openclaw@acd86a0 refactor: move memory embeddings into provider plugins · openclaw/openclaw@77e6e4c test: reuse system-run temp fixtures · openclaw/openclaw@7e9ff0f test: trim hotspot wait overhead · openclaw/openclaw@12a59b0 Check: avoid duplicate boundary prep · openclaw/openclaw@baf11b8 test: reduce hotspot fixture overhead · openclaw/openclaw@3a59edd feat(ui): overhaul settings and slash command UX (#67819) thanks @Bun… · openclaw/openclaw@2cfb660 QA Matrix: exit cleanly on failure · openclaw/openclaw@42805d2 QA Matrix: isolate scenario coverage · openclaw/openclaw@7e659e1 Matrix: refresh crypto bootstrap state · openclaw/openclaw@94081d8 QA Lab: add provider registry · openclaw/openclaw@bb7e982 Matrix: add plugin changelog · openclaw/openclaw@4acab55 test: trim more hotspot overhead · openclaw/openclaw@f485311 test: trim remaining hotspot tests · openclaw/openclaw@6ba8626 test: narrow hotspot mocks · openclaw/openclaw@dbc8179 test: isolate gemini embedding request helpers · openclaw/openclaw@cd330f5 test: trim memory and mcp hotspots · openclaw/openclaw@fd48dfa test: slim provider registry mocks · openclaw/openclaw@2e08c77 test: harden Parallels update smoke · openclaw/openclaw@1a98090 feat: default Anthropic to Opus 4.7 · openclaw/openclaw@628b454 fix: harden node-host shell payload mutability checks · openclaw/openclaw@75c551e fix: land node-host approval binding for native binaries (#66731) (th… · openclaw/openclaw@29919bb CI: add daily schedule to CodeQL workflow (#67645) · openclaw/openclaw@69d25f5 fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… · openclaw/openclaw@c3c7a99 fix: restrict HTML timeout short-circuit to transient statuses · openclaw/openclaw@de129a6 fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) · openclaw/openclaw@3525273 Gateway/skills: dedupe skills prefix-match + drop dead fallback on log · openclaw/openclaw@d7f489f Extensions/lmstudio: back off inference preload after consecutive fai… · openclaw/openclaw@b555214 TUI/streaming: add watchdog that resets the activity indicator after … · openclaw/openclaw@f44ab20 Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write · openclaw/openclaw@b23d59a fix: classify HTML provider error pages correctly (#67642) (thanks @s… · openclaw/openclaw@e588e90 fix(skills): remove unused model-usage import (#67641) · openclaw/openclaw@55f05df docs(changelog): credit codex fix superseded PRs · openclaw/openclaw@e485f24 fix(openai-codex): normalize stale transport metadata in resolution a… · openclaw/openclaw@90801ba CI: pin Docker-related GitHub Actions (#67632) · openclaw/openclaw@f697b01 Android: modernize WebView and discovery API usage (#67627) · openclaw/openclaw@44a6e50 fix(deps): bump hono to 4.12.14 and @hono/node-server to 1.19.14 (GHS… · openclaw/openclaw@fbccc18 fix(deps): bump dompurify to 3.4.0 (#67614) · openclaw/openclaw@2c2dc00 CI: add explicit permissions to all workflow jobs (fixes code-scannin… · openclaw/openclaw@01b7516 fix: register bundled TTS providers and route overrides correctly (#6… · openclaw/openclaw@6ea3cdd fix: align host tilde paths with OS home (#62804) (thanks @stainlu) · openclaw/openclaw@ecfaf64 fix: flush creds queue before reconnect socket open (#67464) (thanks … · openclaw/openclaw@405c63f fix: strip standalone <function> tool call tags from visible text (#6… · openclaw/openclaw@78df859 fix(agents): preserve cli session metadata before transcript persist … · openclaw/openclaw@898fd04 docs(changelog): move cli transcript entry · openclaw/openclaw@c1817c6 fix(agents): normalize cli transcript api field · openclaw/openclaw@3a3fae0 docs(changelog): note cli transcript persistence · openclaw/openclaw@6c343f1 fix(agents): persist cli transcript turns · openclaw/openclaw@b8ef507 fix(msteams): harden security-sensitive flows (#65841) · openclaw/openclaw@c56b56e [Dashboard] Fix exec approval modal overflow for long command content… · openclaw/openclaw@053c5b0 Docs: remove QA changelog entry · openclaw/openclaw@7fd5771 QA: fix private runtime source loading (#67428) · openclaw/openclaw@d5933af docs(gateway): correct protocol.md schema path, hello-ok example, aut… · openclaw/openclaw@489404d CI: pin Node 22 runners to 22.18.0 · openclaw/openclaw@4ffa621 models.authStatus: normalize provider ids + tighten env-backed escape… · openclaw/openclaw@f2fdb9d Update CHANGELOG.md · openclaw/openclaw@7694a92 test(parallels): clean up npm update guard jobs · openclaw/openclaw@045ea7b Plugins: prefer scanDir override paths · openclaw/openclaw@b2974da fix(dreaming): default storage.mode to "separate" so phase blocks sto… · openclaw/openclaw@8c392f0 fix(memory-core): skip dreaming transcript ingestion via session stor… · openclaw/openclaw@a1b01f0 fix: dedupe replayed exec.finished node events (#67281) · openclaw/openclaw@5dcf526
fix(exec): skip node approval prepare in yolo mode · openclaw/openclaw@acd1bd7
steipete · 2026-04-27 · via Recent Commits to openclaw:main

@@ -0,0 +1,312 @@

1+

import crypto from "node:crypto";

2+

import type { AgentToolResult } from "@mariozechner/pi-agent-core";

3+

import {

4+

type ExecApprovalsFile,

5+

type ExecAsk,

6+

type ExecSecurity,

7+

type SystemRunApprovalPlan,

8+

evaluateShellAllowlist,

9+

hasDurableExecApproval,

10+

resolveExecApprovalsFromFile,

11+

} from "../infra/exec-approvals.js";

12+

import {

13+

describeInterpreterInlineEval,

14+

detectInterpreterInlineEvalArgv,

15+

} from "../infra/exec-inline-eval.js";

16+

import { buildNodeShellCommand } from "../infra/node-shell.js";

17+

import { parsePreparedSystemRunPayload } from "../infra/system-run-approval-context.js";

18+

import type { ExecuteNodeHostCommandParams } from "./bash-tools.exec-host-node.js";

19+

import type { ExecToolDetails } from "./bash-tools.exec-types.js";

20+

import { callGatewayTool } from "./tools/gateway.js";

21+

import { listNodes, resolveNodeIdFromList } from "./tools/nodes-utils.js";

22+23+

export type NodeExecutionTarget = {

24+

nodeId: string;

25+

platform?: string | null;

26+

argv: string[];

27+

env: Record<string, string> | undefined;

28+

invokeTimeoutMs: number;

29+

};

30+31+

export type PreparedNodeRun = {

32+

plan: SystemRunApprovalPlan;

33+

argv: string[];

34+

rawCommand: string;

35+

cwd: string | undefined;

36+

agentId: string | undefined;

37+

sessionKey: string | undefined;

38+

};

39+40+

export type NodeApprovalAnalysis = {

41+

analysisOk: boolean;

42+

allowlistSatisfied: boolean;

43+

durableApprovalSatisfied: boolean;

44+

inlineEvalHit: ReturnType<typeof detectInterpreterInlineEvalArgv>;

45+

};

46+47+

export function shouldSkipNodeApprovalPrepare(params: {

48+

hostSecurity: ExecSecurity;

49+

hostAsk: ExecAsk;

50+

strictInlineEval?: boolean;

51+

}): boolean {

52+

return (

53+

params.hostSecurity === "full" && params.hostAsk === "off" && params.strictInlineEval !== true

54+

);

55+

}

56+57+

export function formatNodeRunToolResult(params: {

58+

raw: unknown;

59+

startedAt: number;

60+

cwd: string | undefined;

61+

}): AgentToolResult<ExecToolDetails> {

62+

const payload =

63+

params.raw && typeof params.raw === "object"

64+

? (params.raw as { payload?: unknown }).payload

65+

: undefined;

66+

const payloadObj =

67+

payload && typeof payload === "object" ? (payload as Record<string, unknown>) : {};

68+

const stdout = typeof payloadObj.stdout === "string" ? payloadObj.stdout : "";

69+

const stderr = typeof payloadObj.stderr === "string" ? payloadObj.stderr : "";

70+

const errorText = typeof payloadObj.error === "string" ? payloadObj.error : "";

71+

const success = typeof payloadObj.success === "boolean" ? payloadObj.success : false;

72+

const exitCode = typeof payloadObj.exitCode === "number" ? payloadObj.exitCode : null;

73+

return {

74+

content: [

75+

{

76+

type: "text",

77+

text: stdout || stderr || errorText || "",

78+

},

79+

],

80+

details: {

81+

status: success ? "completed" : "failed",

82+

exitCode,

83+

durationMs: Date.now() - params.startedAt,

84+

aggregated: [stdout, stderr, errorText].filter(Boolean).join("\n"),

85+

cwd: params.cwd,

86+

} satisfies ExecToolDetails,

87+

};

88+

}

89+90+

export async function resolveNodeExecutionTarget(

91+

params: ExecuteNodeHostCommandParams,

92+

): Promise<NodeExecutionTarget> {

93+

if (params.boundNode && params.requestedNode && params.boundNode !== params.requestedNode) {

94+

throw new Error(`exec node not allowed (bound to ${params.boundNode})`);

95+

}

96+

const nodeQuery = params.boundNode || params.requestedNode;

97+

const nodes = await listNodes({});

98+

if (nodes.length === 0) {

99+

throw new Error(

100+

"exec host=node requires a paired node (none available). This requires a companion app or node host.",

101+

);

102+

}

103+

let nodeId: string;

104+

try {

105+

nodeId = resolveNodeIdFromList(nodes, nodeQuery, !nodeQuery);

106+

} catch (err) {

107+

if (!nodeQuery && String(err).includes("node required")) {

108+

throw new Error(

109+

"exec host=node requires a node id when multiple nodes are available (set tools.exec.node or exec.node).",

110+

{ cause: err },

111+

);

112+

}

113+

throw err;

114+

}

115+

const nodeInfo = nodes.find((entry) => entry.nodeId === nodeId);

116+

const supportsSystemRun = Array.isArray(nodeInfo?.commands)

117+

? nodeInfo?.commands?.includes("system.run")

118+

: false;

119+

if (!supportsSystemRun) {

120+

throw new Error(

121+

"exec host=node requires a node that supports system.run (companion app or node host).",

122+

);

123+

}

124+125+

return {

126+

nodeId,

127+

platform: nodeInfo?.platform,

128+

argv: buildNodeShellCommand(params.command, nodeInfo?.platform),

129+

env: params.requestedEnv ? { ...params.requestedEnv } : undefined,

130+

invokeTimeoutMs: Math.max(

131+

10_000,

132+

(typeof params.timeoutSec === "number" ? params.timeoutSec : params.defaultTimeoutSec) *

133+

1000 +

134+

5_000,

135+

),

136+

};

137+

}

138+139+

export function buildNodeSystemRunInvoke(params: {

140+

target: NodeExecutionTarget;

141+

command: string[];

142+

rawCommand: string;

143+

cwd: string | undefined;

144+

timeoutSec: number | undefined;

145+

agentId: string | undefined;

146+

sessionKey: string | undefined;

147+

approved?: boolean;

148+

approvalDecision?: "allow-once" | "allow-always" | null;

149+

runId?: string;

150+

suppressNotifyOnExit?: boolean;

151+

notifyOnExit?: boolean;

152+

systemRunPlan?: SystemRunApprovalPlan;

153+

}): Record<string, unknown> {

154+

return {

155+

nodeId: params.target.nodeId,

156+

command: "system.run",

157+

params: {

158+

command: params.command,

159+

rawCommand: params.rawCommand,

160+

...(params.systemRunPlan ? { systemRunPlan: params.systemRunPlan } : {}),

161+

...(params.cwd != null ? { cwd: params.cwd } : {}),

162+

env: params.target.env,

163+

timeoutMs: typeof params.timeoutSec === "number" ? params.timeoutSec * 1000 : undefined,

164+

agentId: params.agentId,

165+

sessionKey: params.sessionKey,

166+

approved: params.approved,

167+

approvalDecision: params.approvalDecision ?? undefined,

168+

runId: params.runId ?? undefined,

169+

suppressNotifyOnExit:

170+

params.suppressNotifyOnExit === true || params.notifyOnExit === false ? true : undefined,

171+

},

172+

idempotencyKey: crypto.randomUUID(),

173+

};

174+

}

175+176+

export async function invokeNodeSystemRunDirect(params: {

177+

request: ExecuteNodeHostCommandParams;

178+

target: NodeExecutionTarget;

179+

}): Promise<AgentToolResult<ExecToolDetails>> {

180+

const startedAt = Date.now();

181+

const raw = await callGatewayTool(

182+

"node.invoke",

183+

{ timeoutMs: params.target.invokeTimeoutMs },

184+

buildNodeSystemRunInvoke({

185+

target: params.target,

186+

command: params.target.argv,

187+

rawCommand: params.request.command,

188+

cwd: params.request.workdir,

189+

timeoutSec: params.request.timeoutSec,

190+

agentId: params.request.agentId,

191+

sessionKey: params.request.sessionKey,

192+

notifyOnExit: params.request.notifyOnExit,

193+

}),

194+

);

195+

return formatNodeRunToolResult({ raw, startedAt, cwd: params.request.workdir });

196+

}

197+198+

export async function prepareNodeSystemRun(params: {

199+

request: ExecuteNodeHostCommandParams;

200+

target: NodeExecutionTarget;

201+

}): Promise<PreparedNodeRun> {

202+

const prepareRaw = await callGatewayTool(

203+

"node.invoke",

204+

{ timeoutMs: 15_000 },

205+

{

206+

nodeId: params.target.nodeId,

207+

command: "system.run.prepare",

208+

params: {

209+

command: params.target.argv,

210+

rawCommand: params.request.command,

211+

...(params.request.workdir != null ? { cwd: params.request.workdir } : {}),

212+

agentId: params.request.agentId,

213+

sessionKey: params.request.sessionKey,

214+

},

215+

idempotencyKey: crypto.randomUUID(),

216+

},

217+

);

218+

const prepared = parsePreparedSystemRunPayload(prepareRaw?.payload);

219+

if (!prepared) {

220+

throw new Error("invalid system.run.prepare response");

221+

}

222+

return {

223+

plan: prepared.plan,

224+

argv: prepared.plan.argv,

225+

rawCommand: prepared.plan.commandText,

226+

cwd: prepared.plan.cwd ?? params.request.workdir,

227+

agentId: prepared.plan.agentId ?? params.request.agentId,

228+

sessionKey: prepared.plan.sessionKey ?? params.request.sessionKey,

229+

};

230+

}

231+232+

export async function analyzeNodeApprovalRequirement(params: {

233+

request: ExecuteNodeHostCommandParams;

234+

target: NodeExecutionTarget;

235+

prepared: PreparedNodeRun;

236+

hostSecurity: ExecSecurity;

237+

hostAsk: ExecAsk;

238+

}): Promise<NodeApprovalAnalysis> {

239+

const baseAllowlistEval = evaluateShellAllowlist({

240+

command: params.request.command,

241+

allowlist: [],

242+

safeBins: new Set(),

243+

cwd: params.request.workdir,

244+

env: params.request.env,

245+

platform: params.target.platform,

246+

trustedSafeBinDirs: params.request.trustedSafeBinDirs,

247+

});

248+

let analysisOk = baseAllowlistEval.analysisOk;

249+

let allowlistSatisfied = false;

250+

let durableApprovalSatisfied = false;

251+

const inlineEvalHit =

252+

params.request.strictInlineEval === true

253+

? (baseAllowlistEval.segments

254+

.map((segment) =>

255+

detectInterpreterInlineEvalArgv(segment.resolution?.effectiveArgv ?? segment.argv),

256+

)

257+

.find((entry) => entry !== null) ?? null)

258+

: null;

259+

if (inlineEvalHit) {

260+

params.request.warnings.push(

261+

`Warning: strict inline-eval mode requires explicit approval for ${describeInterpreterInlineEval(

262+

inlineEvalHit,

263+

)}.`,

264+

);

265+

}

266+

if ((params.hostAsk === "always" || params.hostSecurity === "allowlist") && analysisOk) {

267+

try {

268+

const approvalsSnapshot = await callGatewayTool<{ file: string }>(

269+

"exec.approvals.node.get",

270+

{ timeoutMs: 10_000 },

271+

{ nodeId: params.target.nodeId },

272+

);

273+

const approvalsFile =

274+

approvalsSnapshot && typeof approvalsSnapshot === "object"

275+

? approvalsSnapshot.file

276+

: undefined;

277+

if (approvalsFile && typeof approvalsFile === "object") {

278+

const resolved = resolveExecApprovalsFromFile({

279+

file: approvalsFile as ExecApprovalsFile,

280+

agentId: params.request.agentId,

281+

overrides: { security: "full" },

282+

});

283+

// Allowlist-only precheck; safe bins are node-local and may diverge.

284+

const allowlistEval = evaluateShellAllowlist({

285+

command: params.request.command,

286+

allowlist: resolved.allowlist,

287+

safeBins: new Set(),

288+

cwd: params.request.workdir,

289+

env: params.request.env,

290+

platform: params.target.platform,

291+

trustedSafeBinDirs: params.request.trustedSafeBinDirs,

292+

});

293+

durableApprovalSatisfied = hasDurableExecApproval({

294+

analysisOk: allowlistEval.analysisOk,

295+

segmentAllowlistEntries: allowlistEval.segmentAllowlistEntries,

296+

allowlist: resolved.allowlist,

297+

commandText: params.prepared.rawCommand,

298+

});

299+

allowlistSatisfied = allowlistEval.allowlistSatisfied;

300+

analysisOk = allowlistEval.analysisOk;

301+

}

302+

} catch {

303+

// Fall back to requiring approval if node approvals cannot be fetched.

304+

}

305+

}

306+

return {

307+

analysisOk,

308+

allowlistSatisfied,

309+

durableApprovalSatisfied,

310+

inlineEvalHit,

311+

};

312+

}