Grades are a hygiene check, not a security guarantee.

Claude Code, Plugin

Pm Agent

Senior product partner for strategy, discovery, prioritization, metrics, economics, AI products, PRDs and authorized implementation, with evidence-aware decisions and resumable state.

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

PERMISSION_SHELL_DECLARED OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

Why this grade

  • PERMISSION_SHELL_DECLARED Note

    Runs shell commands, and the manifest or description says so.

    evals/decision-memory/check_snapshots.py, line 27 result = subprocess.run([sys.executable, '-B', str(args.helper), 'status', str(root)], capture_output=True, text=True)

  • OBFUSCATION_FILE_OVER_READ_CAP Note

    A file was over the read cap and was not fully read.

    evals/runtime-pm/bundle-provenance.json, line 1 {

  • OBFUSCATION_FILE_CAP_REACHED Note

    The 400 file cap was reached before every file was read.

    evals/runtime-pm/bundle-provenance.json, line 1 {

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

    evals/decision-memory/check_snapshots.py, line 27

    result = subprocess.run([sys.executable, '-B', str(args.helper), 'status', str(root)], capture_output=True, text=True)

    evals/product-loop/comparison/candidate-snapshot/skills/pm-workflow/examples/experiment-loop/run_example.py, line 24

    result = subprocess.run([sys.executable, "-B", str(SCRIPTS / helper), *map(str, arguments)],

    evals/product-loop/comparison/runs/A-recover--candidate--attempt-01/commands.json, line 94

    "command": "/bin/bash -lc \"python - <<'PY'\nfrom pathlib import Path\nimport json,hashlib,subprocess,re\np=Path('.pm-agent/assistflow')\ns=json.loads((p/'state.json').read_text())

    Show more

    evals/product-loop/comparison/runs/A-recover--candidate--attempt-01/commands.json, line 100

    "command": "/bin/bash -lc \"python - <<'PY'\nimport json,subprocess\nr=json.loads(subprocess.check_output(['python','/root/.agents/skills/pm-workflow/scripts/pm_decisions.py','stat

    evals/product-loop/comparison/runs/A-recover--pawel--attempt-01/commands.json, line 46

    "command": "/bin/bash -lc \"python - <<'PY'\nimport hashlib,json,re,subprocess\nfrom pathlib import Path\nm=json.loads(Path('analysis/input-manifest.json').read_text())['sha256']\n

    evals/runtime-pm/harness/hydrate_public_inputs.py, line 71

    result = subprocess.run(

    evals/runtime-pm/harness/prepare_bundles.py, line 337

    result = subprocess.run(['git', '-C', str(root), 'rev-parse', 'HEAD'], capture_output=True, text=True, check=True)

    evals/runtime-pm/harness/runner/codex_runner.py, line 67

    completed = subprocess.run(

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Pass

    No network call found.

  • Secrets

    Pass

    No read of a credential file or secret environment variable found.

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read. the file cap was reached before every file was read.

    OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

    evals/runtime-pm/bundle-provenance.json, line 1

    {

    evals/runtime-pm/export-manifest.json, line 1

    {

    evals/runtime-pm/answers/R083/final.md, line 1

    Propongo cuatro tickets ordenados. El primer incremento permite cargar y revisar un CSV sin guardar asignaciones; la confirmación completa el recorrido. Las estimaciones redistribu

  • 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 8352fb87b7c5. requests shell access. The manifest names this permission. a file was over the read cap and was not fully read. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: 8352fb87b7c59c5ad69b5dc9b93e69f1fb524328

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.

Read how this letter is chosen