mcp@3.25.3
CAUTION· startup onlyPublisher claims: "Official 0xinsider CLI and MCP server: Polymarket analytics & infrastructure for sports and esports markets" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
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
API_KEY_ENV_VARAPI_KEY_PREFIXOXINSIDER_API_KEYConfiguration, not credentials: NEUTRALIZED_META_KEY, OXINSIDER_API_URL, OXINSIDER_CONFIG_DIR- Where it talks to
- 0xinsider.com (its own)Also rfc-editor.org, nodejs.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
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names rfc-editor.org, nodejs.org as well as its own vendor. The guard injects API_KEY_ENV_VAR, API_KEY_PREFIX, OXINSIDER_API_KEY only into requests to 0xinsider.com (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 3.25.1
vet-skills diff mcp 3.25.1 3.25.3In the sandbox, this version reached for nothing 3.25.1 did not. Compared from the two recorded runs, not from source.
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; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 78/100 (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; Access to sensitive file paths; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 29 s · 2 scenarios · 0 deviationsStatic findings
[mcp_servers."${SERVER_NAME}".env]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.console.log("Replace the placeholder with your API key in the config file. Do not paste the key into a command or terminal output.");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.npx -y ${PACKAGE_NAME}Fix: Pin versions and sources; vendor anything fetched at install time.npx -y ${PACKAGE_NAME} initFix: Pin versions and sources; vendor anything fetched at install time.`[mcp_servers."${SERVER_NAME}".env]`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* without removing it (kill -9, a crash, power loss). An abandoned lock is takenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.The `batch_get_traders`, `batch_get_market_flow` and `batch_get_market_intel` rows below are GENERATED: they publish the batch item cap, which is owned by `MAX_Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.`[mcp_servers.${SERVER_NAME}.env]`,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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
No advisories in OSV for @0xinsider/mcp@3.25.3 as of 22 min ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim 0xinsider: 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.
- 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.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.