Grades are a hygiene check, not a security guarantee.

Claude Code, Plugin

Qdrant Skills

Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, and Java.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

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

Rescanned at commit d2127f6e1b9c, unchanged since the check below.

PERMISSION_SHELL_UNDECLARED

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    scripts/run_eval.py, line 51 result = subprocess.run(

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

    requests shell access. No manifest field names shell or command execution. can delete files.

    PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES

    scripts/run_eval.py, line 51

    result = subprocess.run(

    scripts/test_make_links_absolute.py, line 64

    shutil.rmtree(self.tmp)

    scripts/scoring/judge.py, line 322

    proc = 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

    scripts/validate_skills.py, line 77

    # qdrant-clients-sdk is a leaf that needs Bash for curl snippet search

    skills/qdrant-clients-sdk/SKILL.md, line 35

    curl -X GET "https://skills.qdrant.tech/snippets/search?language=python&query=how+to+upload+points"

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    scripts/scoring/judge.py, line 303

    """Populate ANTHROPIC_API_KEY from .env if not already in the environment."""

    scripts/scoring/judge.py, line 304

    if os.environ.get("ANTHROPIC_API_KEY"):

    scripts/scoring/judge.py, line 306

    env = repo_root / ".env"

    Show more

    skill-test/scripts/run-claude-session.sh, line 8

    if [[ -f "$REPO_ROOT/.env" ]]; then

    skill-test/scripts/run-claude-session.sh, line 9

    ENV_FILE="$REPO_ROOT/.env"

    skill-test/scripts/run-claude-session.sh, line 33

    --env-file FILE Docker env-file with credentials. Defaults to .env if present.

    skill-test/scripts/run-claude-session.sh, line 48

    Put ANTHROPIC_API_KEY=... in .env, pass --env-file, or export it in your shell.

    skill-test/scripts/run-claude-session.sh, line 223

    Set ANTHROPIC_API_KEY in .env, pass --env-file with a non-empty key, or export

    skill-test/scripts/run-claude-test.sh, line 9

    if [[ -f "$REPO_ROOT/.env" ]]; then

  • 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.

    OBFUSCATION_FILE_OVER_READ_CAP

    evals/weekly/20260808/scores.csv, line 1

    prompt,skill,model,condition,rep,item_type,item_text,verdict,credit,contribution,contested,evidence_quote

    evals/weekly/20260929T101319Z/scores.csv, line 1

    prompt,skill,model,condition,rep,item_type,item_text,verdict,credit,contribution,contested,evidence_quote

  • 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 d2127f6e1b9c. requests shell access. No manifest field names shell or command execution. can delete files. 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.

Date and source

Date checked:

View source

github.com

Commit graded: d2127f6e1b9c6611fff10fe939c6fb17761aaec2

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