Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

Eregion Job Finding Agent

Eregion Job Finding Agent, a skill listed in the PlugVet directory.

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_DELETE_FILES INSTALL_UNPINNED NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV SECRETS_ENV_READ OBFUSCATION_FILE_OVER_READ_CAP OBFUSCATION_FILE_CAP_REACHED

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    backend/eregion/runtime/career/jobspy_source.py, line 113 process = subprocess.Popen([config.python, '-c', WORKER, json.dumps(args)], stdout=subprocess.PIPE,

  • INSTALL_UNPINNED Low

    Dependencies use a range or git URL with no lockfile.

    requirements.txt, line 1 langchain-core

  • NETWORK_NO_FIXED_HOST Low

    Makes a network call whose host is not written as a fixed address.

    backend/eregion/runtime/career/discovery.py, line 184 value = fetch()

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    backend/eregion/domain/model.py, line 19 DEFAULT_ENV_PATH = PROJECT_ROOT / ".env"

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    backend/eregion/domain/model.py, line 62 if not (os.getenv('JOB_AGENT_TASK_MAX_INPUT_TOKENS', '').strip() or os.getenv('JOB_AGENT_EXPERIMENT_ID', '').strip()):

  • OBFUSCATION_FILE_OVER_READ_CAP Note

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

    backend/eregion/runtime/career/board_directory.json, line 1 [

  • OBFUSCATION_FILE_CAP_REACHED Note

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

    backend/eregion/runtime/career/board_directory.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

    Concern

    can delete files.

    PERMISSION_DELETE_FILES

    backend/eregion/runtime/career/jobspy_source.py, line 113

    process = subprocess.Popen([config.python, '-c', WORKER, json.dumps(args)], stdout=subprocess.PIPE,

    backend/eregion/runtime/skills/evolution.py, line 170

    shutil.rmtree(package)

    backend/eregion/runtime/skills/evolution.py, line 423

    shutil.rmtree(temporary)

    Show more

    backend/eregion/runtime/skills/evolution.py, line 505

    shutil.rmtree(published)

    tools/evals/run_ablation.py, line 347

    "git_commit": subprocess.run(

    tools/evals/run_evals.py, line 264

    evaluated_source_commit = subprocess.run(

    tools/evals/run_evals.py, line 268

    subprocess.run(

    tools/evals/run_job_workflow_component_evals.py, line 31

    git_commit = subprocess.run(["git", "rev-parse", "HEAD"], cwd=ROOT.parent,

    tools/evals/run_job_workflow_component_evals.py, line 33

    dirty_before_run = bool(subprocess.run(["git", "status", "--porcelain"],

    tools/evals/run_mock_interview_evals.py, line 101

    source_commit = subprocess.check_output(

    tools/evals/run_requirement_intelligence_v3.py, line 460

    source_commit = subprocess.run(

  • Install and update

    Concern

    dependencies are not pinned.

    INSTALL_UNPINNED

    requirements.txt, line 1

    langchain-core

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    backend/eregion/runtime/career/discovery.py, line 184

    value = fetch()

    frontend/chrome_extension/api-client.js, line 23

    const response = await fetch(`${API_BASE_URL}${path}`, { ...options, headers: { Accept: "application/json", ...(options.body ? { "Content-Type": "application/json" } : {}), ...(opt

    frontend/web_app/apply.js, line 62

    const response=await fetch(routed.url,{method,headers:{'Content-Type':'application/json'},...(body===undefined?{}:{body:JSON.stringify(body)}),signal:AbortSignal.timeout(path==='/r

    Show more

    frontend/web_app/apply.js, line 568

    async function refreshPreview(item){if(previewPending)return;if(terminal.has(item.status)&&!item.browser||(item.career&&!item.application_run_id&&!item.browser))return;previewPendi

    frontend/web_app/browser-control.js, line 17

    const response = await fetch(destination.url, {method:'POST', cache:'no-store',

    frontend/web_app/conversations.js, line 5

    const response=await fetch(url,{method,headers:{'Content-Type':'application/json'},

    tools/scripts/live_apply_meter.py, line 144

    state = json.load(urllib.request.urlopen(f'{BASE}/api/career/tasks/{task_id}', timeout=30))

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    backend/eregion/domain/model.py, line 19

    DEFAULT_ENV_PATH = PROJECT_ROOT / ".env"

    backend/eregion/domain/model.py, line 62

    if not (os.getenv('JOB_AGENT_TASK_MAX_INPUT_TOKENS', '').strip() or os.getenv('JOB_AGENT_EXPERIMENT_ID', '').strip()):

    backend/eregion/domain/model.py, line 248

    raise ValueError("Set LLM_MODEL_ID in the environment or project's .env file.")

    Show more

    backend/eregion/domain/model_settings.py, line 3

    The values live in the project's `.env`, the same file `create_model` reads on every

    backend/eregion/domain/model_settings.py, line 6

    over `.env`; such a field is reported as locked and cannot be changed here. The API key

    backend/eregion/domain/model_settings.py, line 10

    are read through `.env` on each use; the others are read from the process environment, so a

    backend/eregion/domain/model_settings.py, line 11

    saved value is also set in this process and loaded from `.env` when the server starts.

    backend/eregion/domain/model_settings.py, line 79

    # Values this process copied from `.env` into its environment; anything else there is the operator's.

    backend/eregion/domain/model_settings.py, line 85

    """The field is set in the server's environment, which overrides `.env`."""

  • 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

    backend/eregion/runtime/career/board_directory.json, line 1

    [

    backend/migrations/versions/0005_create_session_runtime.py, line 1

    """Create versioned session snapshots, messages, and events.

  • 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 c4b8ffc1ba39. can delete files. dependencies are not pinned. can reach a host that is not written as a fixed address. reads a credential or environment file. 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: c4b8ffc1ba396509cf6ba89f1f6b1c28a8851162

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