mcp@1.0.0-beta.12
CAUTION· not startedPublisher claims: "Model Context Protocol server for Besales" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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_PATHor--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.
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.12In 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 deviationsStatic findings
` 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.prettier-ignore-startFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.chmod 700 "$secrets_dir"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.// конверта, поэтому она под тем же флагом: пакет ставится без версии (`npx -y`), иFix: Pin versions and sources; vendor anything fetched at install time.'Update the client (npx -y @besales/mcp@latest) and run `besales-mcp connect` again.'Fix: Pin versions and sources; vendor anything fetched at install time.prettier-ignore-endFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.export declare function createHttpMcpServer(options?: HttpServerOptions): {Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.chmod 600 "$temporary"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.import { runHttpMcpServer } from '../dist/http-server.js';Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.local bridge_text=${BESALES_MCP_BRIDGE:-npx -y @besales/mcp@beta}Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
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%- 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.
- 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.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- 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.