Claude Code, Plugin
mlflow
Skills for tracing, evaluating, and improving AI agents with MLflow.
Compatibility: Not stated.
Grade B
Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 3b0d56a394c3.
NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED SECRETS_ENV_READ
Why this grade
- NETWORK_NO_FIXED_HOST Low
Makes a network call whose host is not written as a fixed address.
querying-mlflow-metrics/scripts/fetch_metrics.py, line 147
with urllib.request.urlopen(req, timeout=30) as response: - SECRETS_PATH_DOTENV Low
Mentions a .env file.
agent-evaluation/SKILL.md, line 128
**If BOTH are already set, skip Steps 1-2 entirely.** The environment is pre-configured. Do NOT run `setup_mlflow.py`, do NOT create a `.env` file, do NOT override these values. Go - PERMISSION_SHELL_DECLARED Note
Runs shell commands, and the manifest or description says so.
agent-evaluation/scripts/create_dataset_template.py, line 110
result = subprocess.run(["python", "-c", code], capture_output=True, text=True, check=True) - SECRETS_ENV_READ Note
Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.
agent-evaluation/scripts/validate_auth.py, line 32
token = os.getenv("DATABRICKS_TOKEN")
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.
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
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
agent-evaluation/scripts/create_dataset_template.py, line 110
result = subprocess.run(["python", "-c", code], capture_output=True, text=True, check=True)
agent-evaluation/scripts/create_dataset_template.py, line 126
result = subprocess.run(["python", "-c", code], capture_output=True, text=True, check=True)
agent-evaluation/scripts/run_evaluation_template.py, line 37
result = subprocess.run(["python", "-c", code], capture_output=True, text=True, check=True)
Show more
agent-evaluation/scripts/setup_mlflow.py, line 79
result = subprocess.run(
agent-evaluation/scripts/validate_environment.py, line 27
result = subprocess.run(["mlflow", "doctor"], capture_output=True, text=True, timeout=10)
agent-evaluation/scripts/utils/env_validation.py, line 111
result = subprocess.run(
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
querying-mlflow-metrics/scripts/fetch_metrics.py, line 147
with urllib.request.urlopen(req, timeout=30) as response:
instrumenting-with-mlflow-tracing/references/distributed-tracing.md, line 23
requests.post(
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_DOTENV
agent-evaluation/scripts/validate_auth.py, line 32
token = os.getenv("DATABRICKS_TOKEN")
agent-evaluation/scripts/validate_auth.py, line 232
if os.getenv("OPENAI_API_KEY"):
agent-evaluation/SKILL.md, line 128
**If BOTH are already set, skip Steps 1-2 entirely.** The environment is pre-configured. Do NOT run `setup_mlflow.py`, do NOT create a `.env` file, do NOT override these values. Go
Show more
agent-evaluation/scripts/validate_auth.py, line 235
if os.getenv("ANTHROPIC_API_KEY"):
agent-evaluation/scripts/validate_auth.py, line 238
if os.getenv("GEMINI_API_KEY") or os.getenv("GOOGLE_API_KEY"):
agent-evaluation/scripts/validate_auth.py, line 241
if os.getenv("DATABRICKS_TOKEN") or os.getenv("DATABRICKS_HOST"):
agent-evaluation/references/setup-guide.md, line 20
**If BOTH variables are already set, skip Steps 1-2 entirely.** The environment is pre-configured by the caller. Do NOT run `setup_mlflow.py`, do NOT create a `.env` file, do NOT o
agent-evaluation/references/setup-guide.md, line 58
- `.env` file (most common)
agent-evaluation/references/setup-guide.md, line 63
- If `.env` exists: Append `MLFLOW_TRACKING_URI` and `MLFLOW_EXPERIMENT_ID`
agent-evaluation/references/setup-guide.md, line 168
⚠️ **Skip this step if MLFLOW_TRACKING_URI and MLFLOW_EXPERIMENT_ID were already set in the environment before setup.** Creating a `.env` file can override the pre-configured value
agent-evaluation/references/setup-guide.md, line 170
Add to .env file:
agent-evaluation/references/setup-guide.md, line 173
cat >> .env << EOF
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 3b0d56a394c3. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 3b0d56a394c3ebfd3bab41d809834dfcfd1db5ef
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.