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

Google DeepMind News
Google DeepMind News
F
Fortinet All Blogs
量子位
G
Google Developers Blog
J
Java Code Geeks
N
Netflix TechBlog - Medium
博客园 - 聂微东
宝玉的分享
宝玉的分享
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
月光博客
月光博客
The Cloudflare Blog
Apple Machine Learning Research
Apple Machine Learning Research
爱范儿
爱范儿
雷峰网
雷峰网
M
MIT News - Artificial intelligence
T
Tailwind CSS Blog
V
Visual Studio Blog
阮一峰的网络日志
阮一峰的网络日志
博客园 - 三生石上(FineUI控件)
Microsoft Azure Blog
Microsoft Azure Blog
aimingoo的专栏
aimingoo的专栏
Martin Fowler
Martin Fowler
有赞技术团队
有赞技术团队
T
The Blog of Author Tim Ferriss

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
fix(security): stop implicit tool grants from config sect...
amknight · 2026-04-30 · via Recent Commits to openclaw:main

@@ -4,6 +4,7 @@ import { DEFAULT_SUBAGENT_MAX_SPAWN_DEPTH } from "../config/agent-limits.js";

44

import { resolveChannelGroupToolsPolicy } from "../config/group-policy.js";

55

import type { OpenClawConfig } from "../config/types.openclaw.js";

66

import type { AgentToolsConfig } from "../config/types.tools.js";

7+

import { logWarn } from "../logger.js";

78

import { normalizeAgentId } from "../routing/session-key.js";

89

import {

910

parseRawSessionConversationRef,

@@ -26,7 +27,11 @@ import {

2627

type SubagentSessionRole,

2728

} from "./subagent-capabilities.js";

2829

import { isToolAllowedByPolicies, isToolAllowedByPolicyName } from "./tool-policy-match.js";

29-

import { normalizeToolName } from "./tool-policy.js";

30+

import {

31+

mergeAlsoAllowPolicy,

32+

normalizeToolName,

33+

resolveToolProfilePolicy,

34+

} from "./tool-policy.js";

30353136

/**

3237

* Tools always denied for sub-agents regardless of depth.

@@ -367,7 +372,9 @@ function hasExplicitToolSection(section: unknown): boolean {

367372

return section !== undefined && section !== null;

368373

}

369374370-

function resolveImplicitProfileAlsoAllow(params: {

375+

/** Detect tool config sections that previously widened profiles implicitly.

376+

* Used only for migration warnings — not merged into profileAlsoAllow. #47487 */

377+

function detectImplicitProfileGrants(params: {

371378

globalTools?: OpenClawConfig["tools"];

372379

agentTools?: AgentToolsConfig;

373380

}): string[] | undefined {

@@ -422,13 +429,33 @@ export function resolveEffectiveToolPolicy(params: {

422429

});

423430

const explicitProfileAlsoAllow =

424431

resolveExplicitProfileAlsoAllow(agentTools) ?? resolveExplicitProfileAlsoAllow(globalTools);

425-

const implicitProfileAlsoAllow = resolveImplicitProfileAlsoAllow({ globalTools, agentTools });

426-

const profileAlsoAllow =

427-

explicitProfileAlsoAllow || implicitProfileAlsoAllow

428-

? Array.from(

429-

new Set([...(explicitProfileAlsoAllow ?? []), ...(implicitProfileAlsoAllow ?? [])]),

430-

)

431-

: undefined;

432+433+

// Warn affected users about removed implicit grants (#47487), but only when

434+

// the active profile/explicit alsoAllow do not already grant those tools.

435+

if (profile) {

436+

const implicitGrants = detectImplicitProfileGrants({ globalTools, agentTools });

437+

if (implicitGrants) {

438+

const profilePolicy = mergeAlsoAllowPolicy(

439+

resolveToolProfilePolicy(profile),

440+

explicitProfileAlsoAllow,

441+

);

442+

const uncovered = implicitGrants.filter(

443+

(toolName) => !isToolAllowedByPolicyName(toolName, profilePolicy),

444+

);

445+

if (uncovered.length > 0) {

446+

logWarn(

447+

`tools policy: profile "${profile}"${agentId ? ` (agent "${agentId}")` : ""} has ` +

448+

`configured tool sections (tools.exec / tools.fs) that no longer implicitly widen ` +

449+

`the profile. Add alsoAllow: [${uncovered.map((t) => `"${t}"`).join(", ")}] ` +

450+

`explicitly if these tools should be available. See #47487.`,

451+

);

452+

}

453+

}

454+

}

455+456+

const profileAlsoAllow = explicitProfileAlsoAllow

457+

? Array.from(new Set(explicitProfileAlsoAllow))

458+

: undefined;

432459

return {

433460

agentId,

434461

globalPolicy: pickSandboxToolPolicy(globalTools),

@@ -437,7 +464,7 @@ export function resolveEffectiveToolPolicy(params: {

437464

agentProviderPolicy: pickSandboxToolPolicy(agentProviderPolicy),

438465

profile,

439466

providerProfile: agentProviderPolicy?.profile ?? providerPolicy?.profile,

440-

// alsoAllow is applied at the profile stage (to avoid being filtered out early).

467+

// alsoAllow is applied at the profile stage to avoid early filtering.

441468

profileAlsoAllow,

442469

providerProfileAlsoAllow: Array.isArray(agentProviderPolicy?.alsoAllow)

443470

? agentProviderPolicy?.alsoAllow