MCP, MCP server
Bench Agent Discovery
Bench Agent Discovery, an MCP server listed in the PlugVet directory.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High finding. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 3d8bc041c679, unchanged since the check below.
PERMISSION_SHELL_UNDECLARED NETWORK_HOST_FROM_INPUT
Why this grade
- PERMISSION_SHELL_UNDECLARED Medium
Runs shell commands that the manifest or description does not mention.
packages/python-sdk/src/bench/cli.py, line 341
installed = subprocess.run(install_args).returncode == 0 - NETWORK_HOST_FROM_INPUT Medium
A file takes a URL or endpoint as input and has no fixed host list.
examples/arxiv-ai-digest/run.py, line 13
with urllib.request.urlopen(url, timeout=15) as r:
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
requests shell access. No manifest field names shell or command execution.
PERMISSION_SHELL_UNDECLARED
packages/python-sdk/src/bench/cli.py, line 341
installed = subprocess.run(install_args).returncode == 0
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Serious
accepts a host from input, with no fixed list in this file.
NETWORK_HOST_FROM_INPUT
examples/arxiv-ai-digest/run.py, line 13
with urllib.request.urlopen(url, timeout=15) as r:
examples/benchmark-runner/run.py, line 110
with urllib.request.urlopen(req, timeout=30) as r:
examples/github-release-radar/run.py, line 20
with urllib.request.urlopen(req, timeout=10) as r:
Show more
examples/hacker-news-signal/run.py, line 11
def fetch(url):
examples/hacker-news-signal/run.py, line 12
with urllib.request.urlopen(url, timeout=8) as r:
examples/hacker-news-signal/run.py, line 27
ids = fetch(HN_TOP)[:30]
examples/hacker-news-signal/run.py, line 31
item = fetch(HN_ITEM.format(sid))
examples/npm-bundle-watch/run.py, line 14
with urllib.request.urlopen(req, timeout=10) as r:
packages/worker/src/oauth.ts, line 52
const tokenRes = await fetch("https://github.com/login/oauth/access_token", {
packages/worker/src/types.ts, line 278
fetch(req: Request): Promise<Response>;
packages/worker/src/types.ts, line 284
fetch(req: Request): Promise<Response>;
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
examples/crewai-agent/index.ts, line 12
apiKey: process.env.BENCH_KEY!,
examples/github-release-radar/run.py, line 12
GITHUB_TOKEN = os.getenv("GITHUB_TOKEN", "")
examples/instrumented-agent/index.ts, line 9
apiKey: process.env.BENCH_KEY!,
Show more
examples/langchain-agent/index.ts, line 13
apiKey: process.env.BENCH_KEY!,
examples/real-research-agent/index.ts, line 17
apiKey: process.env.BENCH_KEY!,
examples/vercel-ai-agent/index.ts, line 13
apiKey: process.env.BENCH_KEY!,
examples/wander-agent/index.ts, line 12
apiKey: process.env.BENCH_KEY!,
packages/adapters/anthropic/src/index.ts, line 50
* const bench = observe({ apiKey: process.env.BENCH_KEY, agent: "my-agent" });
packages/cli/bin/bench.mjs, line 42
bench.agent.json, and writes it to BENCH_KEY in .env. Alternatively, set
packages/cli/src/core.mjs, line 221
const envPath = join(cwd, ".env.example");
packages/cli/src/core.mjs, line 302
const envPath = join(cwd, ".env");
packages/python-sdk/src/bench/cli.py, line 190
env_path = cwd / ".env.example"
.gitignore, line 17
# env
.gitignore, line 18
.env
.gitignore, line 19
.env.local
.gitignore, line 22
!.env.example
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 3d8bc041c679. requests shell access. No manifest field names shell or command execution. accepts a host from input, with no fixed list in this file. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 3d8bc041c67967806e02b8ce0e9b83f8535e11f6
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.