mcp@1.0.0-beta.12

CAUTION· not started

Publisher claims: "Model Context Protocol server for Besales" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher besales · publishing for 191 daysInstalls 1,625Last detonated 19 min 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
BESALES_OAUTH_AUTHORIZE_URLOAUTH_AUTHORIZE_PATHOAUTH_CALLBACK_PATH or --bearer-token-env-varConfiguration, not credentials: BESALES_API_BASE_URL, BESALES_API_CONTRACTS_DIR, BESALES_API_CONTRACTS_ONLY, BESALES_LOCALE, BESALES_MCP_SHIPPED_REGISTRY, BESALES_MOCK_API_PORT, BESALES_WORKSPACE_ID, PACKAGE_PATH, REGISTRY_PATH, SHIPPED_REGISTRY_PATH_ENV
Where it talks to
besales.ai (its own)Also customer.example, example.invalid, api.test — 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 customer.example, example.invalid, api.test as well as its own vendor. The guard injects BESALES_OAUTH_AUTHORIZE_URL, OAUTH_AUTHORIZE_PATH, OAUTH_CALLBACK_PATH only into requests to besales.ai (and its subdomains) and refuses the rest.

$vet-skills run --secrets BESALES_OAUTH_AUTHORIZE_URL=besales.ai,OAUTH_AUTHORIZE_PATH=besales.ai,OAUTH_CALLBACK_PATH=besales.ai -- npx -y @besales/mcp

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

What changed since 1.0.0-beta.5

vet-skills diff mcp 1.0.0-beta.5 1.0.0-beta.12

In the sandbox, this version reached for nothing 1.0.0-beta.5 did not. Compared from the two recorded runs, not from source.

1.0.0-beta.5 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 2026-11-21 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 11 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
11sprocessdependency install exit 1 · (Use `node --trace-warnings ...` to show where the warning was created) npm error Cannot read properties of null (reading 'edgesOut') npm error A complete log of this run can be found in: /tmp/ks-detonate-oAHpeJ/task/home/.npm/_logs/2026-11-21T16_36_56_013Z-debug-0.log
11sclaimednot started: dependency install failed (exit 1); the server itself was not observed
11sprocessscript backend runs setup only
11sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/cli.js:166 · npx invocation of non-well-known package — may execute untrusted code` Update the client (npx -y @besales/mcp@latest) and run \`besales-mcp connect\` again.`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:362 · HTML comment carrying imperative instructions to the agentprettier-ignore-startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File permission modification commandscripts/connect-clients.sh:81 · File permission modification command — agent changes file ownership/permissionschmod 700 "$secrets_dir"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/tools/result.js:221 · npx invocation of non-well-known package — may execute untrusted code// конверта, поэтому она под тем же флагом: пакет ставится без версии (`npx -y`), иFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/auth/oauth-client.js:195 · npx invocation of non-well-known package — may execute untrusted code'Update the client (npx -y @besales/mcp@latest) and run `besales-mcp connect` again.'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:381 · HTML comment carrying imperative instructions to the agentprettier-ignore-endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)dist/http-server.d.ts:10 · MCP server using network transport (SSE/HTTP) — data sent over networkexport declare function createHttpMcpServer(options?: HttpServerOptions): {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File permission modification commandscripts/connect-clients.sh:132 · File permission modification command — agent changes file ownership/permissionschmod 600 "$temporary"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)bin/besales-mcp-http.js:3 · MCP server using network transport (SSE/HTTP) — data sent over networkimport { runHttpMcpServer } from '../dist/http-server.js';Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagescripts/connect-clients.sh:35 · npx invocation of non-well-known package — may execute untrusted codelocal bridge_text=${BESALES_MCP_BRIDGE:-npx -y @besales/mcp@beta}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈48 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim besales: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim besalesPropose a patch to the maintainer