grafana@r12

VERIFIED· install only

Publisher claims: "Configure the connection to Grafana" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Docker MCP CatalogPublisher grafana · publishing for 671 daysInstalls 1.2MLast detonated 41 min ago
$docker run -i --rm mcp/grafana
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · 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
GITHUB_TOKENConfiguration, not credentials: DOCS_INDEX_URL, MCPB_VERSION, RENDERER_LOCAL_DIR
Where it talks to
no vendor host named in the codeAlso grafana.com, grafana.test, githubusercontent.com, slsa.dev, grafana.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 grafana.com, grafana.test, githubusercontent.com, slsa.dev, grafana.invalid 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 -- docker run -i --rm mcp/grafana

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is grafana@r12 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 90/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: build-mcpb: ENOENT: no such file or directory, open '/tmp/ks-detonate-NQTK95/scripts/home/work/acme-api/.claude/skills/draft-release/dist/artifacts.json'
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/uname
0.1sprocessexited 1: mcp-grafana: /tmp/ks-detonate-NQTK95/scripts/home/work/acme-api/.claude/skills/draft-release/linux-x64/mcp-grafana is missing from this bundle
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1: renderer: ENOENT: no such file or directory, open '/tmp/ks-detonate-NQTK95/scripts/home/work/acme-api/.claude/skills/draft-release/ui/mcp-apps/renderer/RENDERER'
0.2sprocess3 of 3 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive file system command detectedDockerfile:31 · Destructive file system command detectedRUN apt-get update && apt-get upgrade -y && apt-get install -y ca-certificates && rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandmcpb/launch.sh:38 · File permission modification command — agent changes file ownership/permissions[ -x "$bin" ] || chmod +x "$bin" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Context shift attemptREADME.md:511 · Context shift attempt — trying to change operational mode · informational: not an instruction file- `--debug`: Enable debug mode for detailed HTTP request/response loggingFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actiontools/testdata/variable_interpolation/README.md:3 · File type combined with upload action — agent may exfiltrate local data files# Variable interpolation golden cases `golden.json` holds 1,600 cases (320 each for prometheus, loki, postgres, mysql and mssql). Each case is an unformatted `$v` reference to a multi-va…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Context shift attemptREADME.md:1050 · Context shift attempt — trying to change operational mode · informational: not an instruction file… "url": "https://localhost:8443/sse" } } } ``` ### Debug Mode You can enable debug mode for the Grafana transport by adding the `-debug` flag to the command. This will…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈1,843 tok
1 file · 80 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.