Skills/PyPI/alpacon-mcp

alpacon-mcp@1.28.0

CAUTION· not started

Publisher claims: "Let AI agents operate your infrastructure under your control. An MCP server that connects agents to Alpacon, which checks each command at runtime, holds risky ones for human approval, and records them for audit." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher alpacax · publishing for 424 daysInstalls 1,809Last 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
ALPACON_MCP_AUTH_ENABLEDConfiguration, not credentials: ALPACON_MCP_CONFIG_FILE, ALPACON_MCP_HOST, ALPACON_MCP_LOG_LEVEL, ALPACON_MCP_PORT, ALPACON_MCP_RESOURCE_URL, ALPACON_MCP_TRANSPORT, ALPACON_MCP_WEBFTP_DOWNLOAD_TIMEOUT, ALPACON_WORK_SESSION, LOG_FORMAT
Where it talks to
alpacon.io, alpacon.ai (its own)Also alpacax.com — 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 alpacax.com as well as its own vendor. The guard injects ALPACON_MCP_AUTH_ENABLED only into requests to alpacon.io (and its subdomains) and refuses the rest.

$vet-skills run --secrets ALPACON_MCP_AUTH_ENABLED=alpacon.io -- uvx alpacon-mcp

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

What changed since 1.20.0

vet-skills diff alpacon-mcp 1.20.0 1.28.0

This version reaches for something 1.20.0 did not: 1 new host (alpacon.ai). Compared from the two recorded runs, not from source.

New hosts
alpacon.ai
No longer contacted
antigravity.google, azure-apim.net, chatgpt.com, claude.ai, claude.com, cursor.com, vscode.dev

1.20.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-22 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Privileged sudo command; Privileged sudo command. 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
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

LOW
Dynamic module loadingtests/test_toolsets.py:154 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandutils/common.py:96 · Privileged sudo command — agent may execute with elevated privileges'before it takes effect, and a session-authorized sudo policy cannot be 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/server_tools.py:477 · Privileged sudo command — agent may execute with elevated privileges'Precondition: the workspace setting "Use sudo with MFA" must be on. 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/command_tools.py:228 · Privileged sudo command — agent may execute with elevated privileges'sudo was denied: this command is not covered by a session-authorized sudo 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/command_tools.py:218 · Privileged sudo command — agent may execute with elevated privileges'with sudo by default; use sudo only when the command genuinely requires root 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandutils/common.py:94 · Privileged sudo command — agent may execute with elevated privileges'This command is not covered by the Work Session sudo policy. You can 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandutils/common.py:47 · Privileged sudo command — agent may execute with elevated privileges# envelope (lowercase code) and the sudo plugin's terminal line (uppercase)—soFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/prompts.py:76 · Privileged sudo command — agent may execute with elevated privilegesdoes not wait: unless a Work Session sudo policy already covers it, the server denies itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/command_tools.py:222 · Privileged sudo command — agent may execute with elevated privileges# Non-interactive sudo denial codes, as they reach the command output viaFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_toolsets.py:272 · Dynamic module loadingassert importlib.util.find_spec('main_sse') is NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/server_tools.py:474 · Privileged sudo command — agent may execute with elevated privileges'Use this on a host provisioned with alpamon alone that needs the PAM module for sudo with MFA. 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/prompts.py:80 · Privileged sudo command — agent may execute with elevated privileges`sudo_denial` says another sudo call was denied outright, `sudo_hint` names that call,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedutils/local_signal.py:502 · Python subprocess execution detectedsubprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Privileged sudo commandtools/server_tools.py:485 · Privileged sudo command — agent may execute with elevated privilegesmeta={'anthropic/searchHint': 'alpamon-pam install pam module sudo mfa'},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_toolsets.py:153 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Refusal suppressiondocs/api-reference.md:518 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileapproval policy blocks script bodies. It is never refused at submit time. The command is created asFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/skill_scripts.py:30 · Python subprocess execution detectedreturn subprocess.run( # noqa: S603 # repository snippets against isolated fakesFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationutils/oauth/_token.py:55 · Credential pass-through configuration — agent relays sensitive credentials"""Proxy token exchange to Auth0, injecting client_id and client_secret; allowsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Destructive file system command detectedDockerfile:25 · Destructive file system command detectedrm -rf /root/.cacheFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collects environment variables by secret-like namesmain.py:33 · Collects environment variables by secret-like namesfor name, value in os.environ.items()Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Privileged sudo commandutils/common.py:98 · Privileged sudo command — agent may execute with elevated privileges'Work Session sudo policy in the Alpacon web console. Retry once the 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandDockerfile:52 · File permission modification command — agent changes file ownership/permissionschown -R alpacon:alpacon /app/logs /app/config /home/alpaconFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Destructive file system command detectedDockerfile:16 · Destructive file system command detectedRUN uv sync --locked --no-dev --no-install-project && rm -rf /root/.cacheFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo commandtests/test_common.py:85 · Privileged sudo command — agent may execute with elevated privilegesassert 'session-authorized sudo policy' in textFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageREADME.md:392 · Authorization escalation language · informational: not an instruction file> *"List all users who can login on server web-01 and check for any users with sudo privileges"*Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python exec or eval of computed codetools/resources.py:448 · Python exec or eval of computed codeexec(compile(src, __file__, 'exec'), ns) # noqa: S102Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
LOW
Authorization escalation languagedocs/api-reference.md:1223 · Authorization escalation language · informational: not an instruction file… `get_workspace_access_control` Get the workspace access control settings: sudo/root access policy (`allow_sudo_with_mfa`, `allow_direct_root`, `block_local_sudo`, `sudo_t…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsserver.py:283 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# main_http.py has no --toolsets flag; a shared .env is the likely source.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commandtools/prompts.py:140 · Privileged sudo command — agent may execute with elevated privileges- Lens 2—Event forensic, cross-session ("every sudo / every `rm -rf` / every transferFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/prompts.py:24 · Privileged sudo command — agent may execute with elevated privilegesWork Session sudo policy already covers the command, a sudo invocation is denied atFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandtools/server_tools.py:479 · Privileged sudo command — agent may execute with elevated privileges'server_pam_install_requires_sudo_with_mfa (sudo with MFA is off—turn the setting on; or this deployment cannot complete its step-up—the workspace cannot fix this, report it to the operator), 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandutils/common.py:104 · Privileged sudo command — agent may execute with elevated privileges'yourself. Wait for the decision, then retry the sudo command; do not 'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Refusal suppressiondocs/api-reference.md:1270 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…extension`), whether `ip` is missing or being removed. Removing an extension is never refused for the plan - `websh_session_timeout` (integer, optional): Websh idle session…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Refusal suppressiondocs/api-reference.md:693 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction filewas never refused.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈7,939 tok
3 files · 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 alpacon-mcp@1.28.0 as of 35 min ago. This is the package itself, not its dependencies.

What would make this Verified

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim alpacax: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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. Collects environment variables by secret-like names≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  5. 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.
  6. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim alpacaxPropose a patch to the maintainer