Skip to content
ai-supply.store
탐색카테고리리더보드커뮤니티Agent APIFAQ
로그인무료 가입
catalog / Agentic capability / XAgent — Autonomous LLM Agent for Complex Tasks
◉AgentAgentic capabilityFree

XAgent — Autonomous LLM Agent for Complex Tasks

Autonomous agent by OpenBMB with outer/inner loop planning, tool execution, and a human-in-the-loop GUI for long-horizon tasks.

@ai-supply
설치 수57k
⟳ upstream v1.0.0 · updated 2y ago
↗ 소스 저장소
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade D · 0/100 · ReviewSecurity assessment
2compromise signals21capabilities surfaced1known CVE7of 20 OWASP controls clear
Verified secret leak (deep scan)Verified secret leak (deep scan)Broad capability surfacePotentially unbounded loop
scanned 18d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

XAgent

XAgent is an experimental open-source autonomous agent designed to solve long-horizon tasks via a two-loop architecture: an outer loop for high-level planning and task decomposition, and an inner loop for tool-calling execution and error recovery.

Key Features

  • Dual-loop design: PlanAgent (outer) + ToolServerInterface (inner)
  • Rich built-in toolset: file I/O, shell, web browser, Python REPL, search
  • Human feedback mode: approve/reject individual steps via web UI
  • Docker sandbox for safe code execution
  • Sub-agent delegation for parallel workstreams
  • Plugin system for custom tools

Quick Start

git clone https://github.com/OpenBMB/XAgent
cd XAgent
docker compose up
# Access UI at http://localhost:5173

Install via ai-supply

npx ai-supply add xagent-autonomous-task-solving

Curated mirror of the open-source XAgent (Apache-2.0). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#26
of 35 in Agentic capability
Security score
0/100 · D
review
Security rank
#35
of 35 in Agentic capability
Installs
57k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 00/100 · grade Dscanned 18d ago
⚠ 2 compromise signals22 risk-surface · 8/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → 127.0.0.1\, 0.0.0.0\, www.deepmind.com, x-agent.net, api.openai.com, open-procedures.replit.app, keepachangelog.com, semver.org +15

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurecompromise · high
Secrets, credentials or PII shipped inside the artifact.
•Verified secret leak (deep scan) — 1 leak(s): github-pat · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/assets/rapidapi_high_quality_apis.json (CWE-798)compromise
•Verified secret leak (deep scan) — 1 leak(s): github-pat · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/assets/rapidapi_apis_infos.json (CWE-798)compromise
⚠LLM07System Prompt Leakagecompromise · high
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · OpenBMB-XAgent-3619c25/XAgentWeb/publish_test (CWE-200)risk surface
•Verified secret leak (deep scan) — 1 leak(s): github-pat · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/assets/rapidapi_high_quality_apis.json (CWE-798)compromise
•Verified secret leak (deep scan) — 1 leak(s): github-pat · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/assets/rapidapi_apis_infos.json (CWE-798)compromise
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 9 pip requirements declared · OpenBMB-XAgent-3619c25/ToolServer/ToolServerManager/requirements.txtrisk surface
•Dependency manifest — 38 pip requirements declared · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/requirements.txtrisk surface
•Dependency manifest — 29 pip requirements declared · OpenBMB-XAgent-3619c25/XAgentGen/requirements.txtrisk surface
•Dependency manifest — 59 npm dependencies declared · OpenBMB-XAgent-3619c25/XAgentWeb/package.jsonrisk surface
•Dependency manifest — 31 pip requirements declared · OpenBMB-XAgent-3619c25/requirements.txtrisk surface
•Vulnerable dependencies — 341 known vulnerabilities in: fastapi@0.99.1, httpx@0.9.5, uvicorn@0.9.1, h11@0.8.1, h2@3.2.0, idna@2.9.0, starlette@0.27.0, orjson@3.9.9 (CWE-1395)known CVE · -25 pts
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — unsafe yaml.load · OpenBMB-XAgent-3619c25/ToolServer/ToolServerManager/config.py (CWE-502)expected
•Suspicious code patterns — dynamic code execution · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/core/register/register.py (CWE-95)expected
•Suspicious code patterns — OS command execution · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/extensions/envs/shell.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · OpenBMB-XAgent-3619c25/dockerfiles/ToolServerNode/Dockerfile (CWE-78)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 4 distinct host(s) · OpenBMB-XAgent-3619c25/CHANGELOG.mdexpected
•External endpoints declared — 2 distinct host(s) · OpenBMB-XAgent-3619c25/CODE_OF_CONDUCT.mdexpected
•External endpoints declared — 1 distinct host(s) · OpenBMB-XAgent-3619c25/CONTRIBUTING.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · OpenBMB-XAgent-3619c25/README.md (CWE-272)risk surface
•External endpoints declared — 14 distinct host(s) · OpenBMB-XAgent-3619c25/README.mdexpected
•External endpoints declared — 13 distinct host(s) · OpenBMB-XAgent-3619c25/README_JA.mdexpected
•Egress to a private/loopback host — 127.0.0.1, 0.0.0.0 · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/core/envs/web.py (CWE-918)expected
•Egress to a private/loopback host — 127.0.0.1 · OpenBMB-XAgent-3619c25/XAgent/ai_functions/request/xagent.py (CWE-918)expected
•External endpoints declared — 3 distinct host(s) · OpenBMB-XAgent-3619c25/XAgentGen/README.mdexpected
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · OpenBMB-XAgent-3619c25/ToolServer/ToolServerManager/node_checker.py (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 9 pip requirements declared · OpenBMB-XAgent-3619c25/ToolServer/ToolServerManager/requirements.txtrisk surface
•Dependency manifest — 38 pip requirements declared · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/requirements.txtrisk surface
•Dependency manifest — 29 pip requirements declared · OpenBMB-XAgent-3619c25/XAgentGen/requirements.txtrisk surface
•Dependency manifest — 59 npm dependencies declared · OpenBMB-XAgent-3619c25/XAgentWeb/package.jsonrisk surface
•Dependency manifest — 31 pip requirements declared · OpenBMB-XAgent-3619c25/requirements.txtrisk surface
•Vulnerable dependencies — 341 known vulnerabilities in: fastapi@0.99.1, httpx@0.9.5, uvicorn@0.9.1, h11@0.8.1, h2@3.2.0, idna@2.9.0, starlette@0.27.0, orjson@3.9.9 (CWE-1395)known CVE · -25 pts
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — unsafe yaml.load · OpenBMB-XAgent-3619c25/ToolServer/ToolServerManager/config.py (CWE-502)expected
•Suspicious code patterns — dynamic code execution · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/core/register/register.py (CWE-95)expected
•Suspicious code patterns — OS command execution · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/extensions/envs/shell.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf / · OpenBMB-XAgent-3619c25/dockerfiles/ToolServerNode/Dockerfile (CWE-78)expected
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (14) · hygiene / uncategorized
•Unrecognized file type — '.env' is not on the allowlist · OpenBMB-XAgent-3619c25/.envrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · OpenBMB-XAgent-3619c25/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · OpenBMB-XAgent-3619c25/LICENSErisk surface
•Suspicious network references — raw IP URL (11 URLs) · OpenBMB-XAgent-3619c25/ToolServer/ToolServerNode/core/envs/web.pyrisk surface
•Suspicious network references — raw IP URL (1 URLs) · OpenBMB-XAgent-3619c25/XAgent/ai_functions/request/xagent.pyrisk surface
•Unrecognized file type — '.conf' is not on the allowlist · OpenBMB-XAgent-3619c25/XAgentServer/nginx/nginx.confrisk surface
•Suspicious network references — raw IP URL (2 URLs) · OpenBMB-XAgent-3619c25/XAgentServer/nginx/nginx.confrisk surface
•Unrecognized file type — '.local' is not on the allowlist · OpenBMB-XAgent-3619c25/XAgentWeb/.env.development.localrisk surface
•Unrecognized file type — '.production' is not on the allowlist · OpenBMB-XAgent-3619c25/XAgentWeb/.env.productionrisk surface
•Unrecognized file type — '.cjs' is not on the allowlist · OpenBMB-XAgent-3619c25/XAgentWeb/commitlint.config.cjsrisk surface
•Possible obfuscation — very long lines paired with a decode/execute sink · OpenBMB-XAgent-3619c25/XAgentWeb/public/third/mathjax/output/chtml/fonts/tex.js (CWE-506)risk surface
•Unrecognized file type — '.vue' is not on the allowlist · OpenBMB-XAgent-3619c25/XAgentWeb/src/App.vuerisk surface
•Suspicious network references — suspicious TLD (1 URLs) · OpenBMB-XAgent-3619c25/XAgentWeb/src/views/login/login.vuerisk surface
•Suspicious network references — suspicious TLD (3 URLs) · OpenBMB-XAgent-3619c25/dockerfiles/XAgentGen/Dockerfilerisk surface
✔ verified source · pinned OpenBMB-XAgent-3619c25
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/xagent-autonomous-task-solving/check). Click a policy:

Consume XAgent — Autonomous LLM Agent for Complex Tasks programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/xagent-autonomous-task-solving

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/xagent-autonomous-task-solving/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add xagent-autonomous-task-solving

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/xagent-autonomous-task-solving/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "xagent-autonomous-task-solving" })
OpenAPI spec →
vlatest
! Security: Review · 01mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

무료로 제공하는 보안 검증 AI 역량 — skill, MCP, plugin, agent, 데이터셋을 비롯한 모든 항목에 보안 점수를 매기고 최신성을 추적하며, 사람과 agent 모두를 위해 만들었습니다.

api · v3.1status · all green
문의하기
support@ai-supply.storesecurity@ai-supply.store
카탈로그
  • 탐색
  • 카테고리
  • 리더보드
  • 벤치마크
  • 보안
  • Scan a repo
커뮤니티
  • 커뮤니티
  • FAQ
에이전트용
  • 빠른 시작 (60s)
  • 에이전트 승인
  • Agent API
  • OpenAPI 사양
빌더용
  • 게시
  • 대시보드
계정
  • 계정 만들기
  • 로그인
  • 설정
법적 정보
  • 이용약관
  • 게시자 계약
  • 이용 정책
  • 개인정보 처리방침