Skills/npm/jervis-boost-mcp

jervis-boost-mcp@0.18.1

CAUTION· install only

Publisher claims: "Jervis Boost MCP server — exposes project context to AI agents via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher keroloszakaria · publishing for 124 daysInstalls 666Last detonated 2d ago
What would fix thisWatchDispute verdict

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
no credential variables read in the code
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y jervis-boost-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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; 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 · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
Remote installer piped to shelldist/definitions/skills/caveman.md:49 · Remote installer piped to shellcurl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patterndist/definitions/skills/caveman.md:49 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bashFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Access to sensitive file pathsdist/definitions/skills/docker.md:38 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Parameterize via `.env`; never commit real secretsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
HTML comment carrying imperative instructions to the agentdist/definitions/skills/unocss.md:64 · HTML comment carrying imperative instructions to the agentInstead of long class stringsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsdist/definitions/skills/laravel.md:35 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Keep secrets in `.env`; never commit it. Cache config in productionFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Direct script execution from GitHub raw URLdist/definitions/skills/caveman.md:49 · Direct script execution from GitHub raw URL — unverified code sourcecurl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bashFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/definitions/skills/ruflo.md:35 · npx invocation of non-well-known package — may execute untrusted codenpx ruflo@latest initFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/definitions/skills/trpc.md:41 · File type combined with upload action — agent may exfiltrate local data filesreturn ctx.db.user.findUnique({ where: { id: input.id } })Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/definitions/skills/ruflo.md:27 · npx invocation of non-well-known package — may execute untrusted code…ry, self-learning, and 100+ specialized agents to any project. Initialize with `npx ruflo@latest init` or use Path A (plugins only) for a lighter footprint. --- **Setup:*…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/definitions/skills/ruflo.md:42 · npx invocation of non-well-known package — may execute untrusted codeclaude mcp add ruflo -- npx ruflo@latest mcp startFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/definitions/skills/trpc.md:47 · File type combined with upload action — agent may exfiltrate local data filesreturn ctx.db.user.update({ where: { id: input.id }, data: { name: input.name } })Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈61 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for jervis-boost-mcp@0.18.1 as of 2d ago. This is the package itself, not its dependencies.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim keroloszakaria: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. 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.
  5. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim keroloszakariaPropose a patch to the maintainer