Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

SkillAlchemy

From thought to skill.

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.

Rescanned at commit d0f0355a542e, unchanged since the check below.

NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED OBFUSCATION_FILE_OVER_READ_CAP

Why this grade

  • NETWORK_NO_FIXED_HOST Low

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

    skills/LEAP/scripts/build_corpus.py, line 85 with urllib.request.urlopen(req, timeout=REQUEST_TIMEOUT) as resp:

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    skills/agentsop-dify/SKILL.md, line 178 cp .env.example .env

  • PERMISSION_SHELL_DECLARED Note

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

    skills/agentsop-conventions-pinning/SKILL.md, line 176 - Avoid: `os.system` (use `subprocess.run`), `eval`, raw f-strings in logging.

  • OBFUSCATION_FILE_OVER_READ_CAP Note

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

    skills/agentsope-ai-video-director/references/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

    skills/agentsop-conventions-pinning/SKILL.md, line 176

    - Avoid: `os.system` (use `subprocess.run`), `eval`, raw f-strings in logging.

    skills/agentsop-per-model-artifacts/references/R2-versioning-recipes.md, line 99

    "commit": subprocess.check_output(["git","rev-parse","HEAD"]).decode().strip(),

    skills/agentsop-test-fix-loop/SKILL.md, line 162

    result = subprocess.run(

    Show more

    skills/agentsop-test-fix-loop/SKILL.md, line 171

    result = subprocess.run(

    skills/agentsop-conventions-pinning/SKILL.md, line 103

    | Anti-pattern: "Never use `os.system`; use `subprocess.run`." | "TODO: write better docs here." (file is not a TODO list) |

  • 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

    skills/LEAP/scripts/build_corpus.py, line 85

    with urllib.request.urlopen(req, timeout=REQUEST_TIMEOUT) as resp:

    skills/LEAP/scripts/build_corpus.py, line 114

    with urllib.request.urlopen(req, timeout=REQUEST_TIMEOUT) as resp:

    skills/agentsop-conventions-pinning/SKILL.md, line 368

    | 3 | Add a counter-example: "Wrong: `requests.get(url)`. Right: `httpx.get(url, timeout=10)`" |

    Show more

    skills/agentsop-streaming-output/README.md, line 41

    3. **Pick transport**: SSE (receive-only default) / WebSocket (bidirectional) /

    skills/agentsop-streaming-output/README.md, line 67

    Transport is orthogonal: SSE (default) / WebSocket (bidirectional) / async

    skills/agentsop-streaming-output/SKILL.md, line 359

    Transport is **orthogonal** to all four: SSE (default, receive-only), WebSocket

    skills/agentsop-streaming-output/references/R1-source-evidence.md, line 113

    - **SSE is receive-only** → if the client must push mid-stream, use WebSocket

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    skills/agentsop-dify/SKILL.md, line 178

    cp .env.example .env

    skills/agentsop-dify/references/R2-sop-workflow.md, line 38

    cp .env.example .env

    skills/agentsop-dify/references/R2-sop-workflow.md, line 39

    # edit .env: VECTOR_STORE, secrets, ...

  • 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

    skills/agentsope-ai-video-director/references/provenance.json, line 1

    {

  • 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 d0f0355a542e. 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. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: d0f0355a542e922d7d62bc3405bb41b92a52e06d

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