Skills/Glama/mcp-prometheus

mcp-prometheus@0.2.0

VERIFIED· install only

Publisher claims: "Enables agents to query and explore Prometheus through PromQL, metric and label discovery, alerts, rules, scrape health, and cardinality, while keeping admin writes disabled unless explicitly enabled." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher mgcrea · publishing for 120 daysInstalls 0Last detonated 3d ago
$npx skills add mcp-prometheus
WatchReport an issue

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: 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
PROMETHEUS_PASSWORDPROMETHEUS_TOKENConfiguration, not credentials: GIT_COMMIT, GIT_COMMIT_DATE, PROMETHEUS_ALLOW_WRITES, PROMETHEUS_DEBUG, PROMETHEUS_HEADERS, PROMETHEUS_MAX_RETRIES, PROMETHEUS_TIMEOUT, PROMETHEUS_UI_LINKS, PROMETHEUS_URL, PROMETHEUS_USERNAME
Where it talks to
no vendor host named in the codeAlso prometheus.io, unconfigured.invalid — 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 prometheus.io, unconfigured.invalid as well as its own vendor. The guard injects PROMETHEUS_PASSWORD, PROMETHEUS_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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 85/100 (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 · 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
Access to sensitive file paths.github/workflows/ci.yml:74 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),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 package.github/workflows/ci.yml:53 · npx invocation of non-well-known package — may execute untrusted code- name: npx can resolve a bin 🔒Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:60 · npx invocation of non-well-known package — may execute untrusted codeconsole.error('npx cannot pick a bin for ' + pkg.name + ': none of [' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
URL with embedded credentialstest/units.test.ts:144 · URL with embedded credentials — may be phishing or credential leakingconst config = loadConfig({ PROMETHEUS_URL: "https://user:[email protected]" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:48 · npx invocation of non-well-known package — may execute untrusted code# and npx picks the bin by name: it only forgives a mismatch while theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
References a credential file in the home directory.github/workflows/ci.yml:74 · References a credential file in the home directory# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
npx invocation of non-well-known package.github/workflows/ci.yml:47 · npx invocation of non-well-known package — may execute untrusted code# Every client config in the wild spells this server `npx -y <package>`,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Reads credential paths from the home directory.github/workflows/ci.yml:74 · Reads credential paths from the home directory# picked up. For any server that reads one (~/.npmrc, ~/.aws/credentials),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
LOW
Unpinned dependency.github/workflows/ci.yml:150 · Unpinned dependencyrun: npm install -g npm@latestFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

Cost to the agent

Instructions loaded
≈36 tok
1 file · 39 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.