Skills/PyPI/x-use-mcp

x-use-mcp@3.3.0

CAUTION· not started

Publisher claims: "MCP server for X (Twitter): browser research, inbox reads and reviewed publishing. No X API key required." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ihuzaifashoukat · publishing for 121 daysInstalls 404Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
OPENAI_API_KEYConfiguration, not credentials: OPENAI_BASE_URL, OPENAI_MODEL, X_USE_HOME, XUSE_DEV_UNLOCK_DAILY_CAP, XUSE_ENV
Where it talks to
no vendor host named in the codeAlso x.com, openrouter.ai, ipify.org, python.org — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names x.com, openrouter.ai, ipify.org, python.org as well as its own vendor. The guard injects OPENAI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx x-use-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-21 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Credential pass-through configuration; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/xuse/init_wizard.py:141 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesblank lines, unrelated keys) of an existing .env. The header block isFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/xuse/mcp/accounts_tools.py:220 · Credential pass-through configuration — agent relays sensitive credentials"""Show one account's masked config (no cookies, no password, proxyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/xuse/init_wizard.py:316 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_path = PROJECT_ROOT / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/xuse/mcp/drafts.py:10 · Credential pass-through configuration — agent relays sensitive credentials(cookies, API keys, proxy credentials) — only the content to be published.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/xuse/mcp/media.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Do not allow requests to import unrelated credentials from .netrc."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xuse/doctor.py:508 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesload_env() # make .env-provided LLM keys visible to the checks belowFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xuse/init_wizard.py:331 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filestyper.echo("No keys entered — skipping .env.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xuse/init_wizard.py:7 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- .env LLM API keys (never written into settings.json)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xuse/doctor.py:422 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"replace the placeholder with a real key, or remove it from .env so a valid settings.json key can apply")]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Hidden zero-width characters detectedsrc/xuse/browser/page.py:1 · Hidden zero-width characters detected — may conceal content"""Bounded X DOM reads and single-attempt writes using native Playwright.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Access to sensitive file pathssrc/xuse/init_wizard.py:317 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif not typer.confirm("\nSet LLM API keys now (stored in gitignored .env)?", default=True):Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/xuse/doctor.py:418 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"set OPENAI_API_KEY (+ OPENAI_BASE_URL/OPENAI_MODEL) in .env or the llm block in config/settings.json")]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/xuse/mcp/executor.py:300 · Credential pass-through configuration — agent relays sensitive credentialspassword, proxy credentials masked."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/xuse/mcp/executor.py:66 · Credential pass-through configuration — agent relays sensitive credentials# Error sanitizing (NFR-2: never echo cookies, API keys, proxy credentials)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Process kill commandsrc/xuse/browser/sessions.py:259 · Process kill command — agent can terminate processesHandles/pidfds survive driver death and PID reuse. Unsupported atomic killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/xuse/mcp/sessions.py:274 · Process kill command — agent can terminate processes# Shield the startup thread from the timeout: wait_for cannot kill aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/xuse/utils/env.py:1 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""One-time, idempotent loading of the project-root .env file."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
URL with embedded credentialssrc/xuse/utils/proxy_manager.py:116 · URL with embedded credentials — may be phishing or credential leaking- Direct proxy URLs (e.g., http://user:pass@host:port, socks5://host:port)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedsrc/xuse/browser/sessions.py:99 · Python subprocess execution detectedoutput = subprocess.run(["ps", "-axo", "pid=,ppid=,lstart="],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
URL with embedded credentialssrc/xuse/utils/sanitize.py:17 · URL with embedded credentials — may be phishing or credential leaking`http://user:pa/ss@host` it reports no userinfo at all and the credentialFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
URL with embedded credentialssrc/xuse/utils/sanitize.py:3 · URL with embedded credentials — may be phishing or credential leakingMasks the ENTIRE userinfo — `http://user:pass@host`, `http://TOKEN@host`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
URL with embedded credentialssrc/xuse/utils/sanitize.py:14 · URL with embedded credentials — may be phishing or credential leakingthem. `http://user:pa/ss@host` passed through COMPLETELY UNMASKED, andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/xuse/utils/env.py:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Load ``<project_root>/.env`` into ``os.environ`` once per process.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/xuse/mcp/resources.py:11 · Credential pass-through configuration — agent relays sensitive credentialspassword, or proxy credential can leave through this surface.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/xuse/utils/env.py:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_path = Path(PROJECT_ROOT) / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/xuse/queue/runner.py:176 · Credential pass-through configuration — agent relays sensitive credentials# carry proxy credentials (cold-start failures), and last_errorFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationsrc/xuse/mcp/tools.py:176 · Credential pass-through configuration — agent relays sensitive credentialspasswords, proxy credentials masked). Read-only, never starts a browser."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/xuse/utils/env.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPre-existing process environment variables always win over .env valuesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/xuse/init_wizard.py:69 · File type combined with upload action — agent may exfiltrate local data files"community_posting.json": "legacy Selenium: posting into a specific community (async audience unverified)",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/xuse/browser/sessions.py:98 · Process kill command — agent can terminate processes# cannot atomically signal a creation identity. No PID kill fallback.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialssrc/xuse/mcp/proxy_tools.py:190 · URL with embedded credentials — may be phishing or credential leaking"""Mask the whole userinfo: http://user:pass@host:port -> http://***@host:port.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/xuse/utils/env.py:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesIdempotent: later calls are no-ops. A missing .env file is not an error.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
URL with embedded credentialssrc/xuse/utils/sanitize.py:15 · URL with embedded credentials — may be phishing or credential leaking`http://user:p@ss@host` masked only up to the first `@`, leaking the tail.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedsrc/xuse/doctor.py:179 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationsrc/xuse/mcp/resources.py:80 · Credential pass-through configuration — agent relays sensitive credentials"proxy credentials masked.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File type combined with upload actionsrc/xuse/init_wizard.py:65 · File type combined with upload action — agent may exfiltrate local data files"growth.json": "proactive growth: competitor reposts + engagement decisioning",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
URL with embedded credentialssrc/xuse/utils/proxy_manager.py:26 · URL with embedded credentials — may be phishing or credential leaking"""Mask the whole userinfo: http://user:pass@host:port -> http://***@host:port.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
URL with embedded credentialssrc/xuse/models.py:131 · URL with embedded credentials — may be phishing or credential leakingproxy: Optional[str] = Field(default=None, description="Per-account proxy URL, e.g., http://user:pass@host:port or socks5://host:port")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07

Cost to the agent

Instructions loaded
≈61 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for x-use-mcp@3.3.0 as of 46 min ago. This is the package itself, not its dependencies.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ihuzaifashoukat: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  5. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ihuzaifashoukatPropose a patch to the maintainer