Skills/Glama/repograde-mcp

repograde-mcp@0.1.0

VERIFIED· startup only

Publisher claims: "Enables agents to grade any public GitHub repository, returning overall and category scores plus prioritized fixes, and to list all available checks." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher fastpresspages · publishing for 6 daysInstalls 0Last detonated 2 h ago
$npx skills add repograde-mcp
WatchReport an issue

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: Verified 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
GITHUB_TOKEN
Where it talks to
no vendor host named in the codeAlso githubusercontent.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
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 githubusercontent.com as well as its own vendor. The guard injects GITHUB_TOKEN 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 (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-14 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · (node:1771) [UNDICI-EHPA] Warning: EnvHttpProxyAgent is experimental, expect them to change at any time. (Use `node --trace-warnings ...` to show where the warning was created) Usage: repograde owner/repo (try --help)
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageskills/repograde/SKILL.md:18 · npx invocation of non-well-known package — may execute untrusted codenpx -p github:fastpresspages/repograde repograde owner/repoFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/report.js:183 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file'agent.instructions': 'Add AGENTS.md with repo rules for humans and agents.',Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Collapsed <details> block carrying instructionssite/index.html:151 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>Who built this?</summary><p><a href="https://fastpresspages.github.io/YouLauncher/about.html">FastPress Labs</a> — small, free, open source tools for pFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagesrc/checks.js:229 · npx invocation of non-well-known package — may execute untrusted codefixText: 'Package an agent skill (skills/<name>/SKILL.md) so tools can install it with one command (npx skills add owner/repo).',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/report.js:151 · npx invocation of non-well-known package — may execute untrusted codeL.push('Run me again after fixes: `npx repograde owner/repo`.');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/report.js:46 · npx invocation of non-well-known package — may execute untrusted codelines.push(` ${dim('Grade another:')} ${lime('npx repograde owner/repo')}`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/repograde/SKILL.md:47 · npx invocation of non-well-known package — may execute untrusted codegrade_repo / list_checks via `npx -p github:fastpresspages/repograde repograde-mcp` (stdio JSON-RPC).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Collapsed <details> block carrying instructionssite/index.html:149 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>Can this run in CI?</summary><p>Yes — a composite GitHub Action ships in the repo, or call <code>npx -p github:fastpresspages/repograde repograde ownerFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filessrc/checks.js:224 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filefixText: 'Add AGENTS.md telling coding agents the rules of this repo: layout, commands, verification steps, license.',Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Collapsed <details> block carrying instructionssite/index.html:147 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>Is my repo private?</summary><p>RepoGrade only reads public GitHub metadata via the API: root file tree, README, package.json, releases. It cannot see Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageskills/repograde/SKILL.md:3 · npx invocation of non-well-known package — may execute untrusted code… or deciding whether a repo is ready for attention. Zero dependencies; runs via npx with one command; returns a letter grade, six category scores and a prioritized fix …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈1,584 tok
3 files · 63 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

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