Grades are a hygiene check, not a security guarantee.

Claude Code, Plugin

Agent Stdlib

Agent-building practices from Anthropic's engineering blog, packaged as installable Claude Code skills, MCP servers, and safety hooks for tool-gating and prompt-injection screening.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. Only try it in a sandbox.

Graded by PlugVetRubric v2

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

Rescanned at commit 6424ccb8a72e, unchanged since the check below.

SECRETS_PATH_CREDENTIAL AGENT_IGNORE_INSTRUCTIONS

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    hooks/action_gate.py, line 59 (r"(cat|head|tail|echo|printf)\b[^|]*(\.env|secret|token|api[_-]?key|password|id_rsa|credential)[^|]*\|\s*(curl|wget|nc)\b",

  • AGENT_IGNORE_INSTRUCTIONS Medium

    Text tells the agent to ignore earlier instructions.

    hooks/README.md, line 78 ignore prior instructions, forged system turns, secrecy or exfiltration

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.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

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

    mcp-servers/code-execution/server.py, line 131

    proc = subprocess.run(

  • Install and update

    Pass

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

  • Network

    Pass

    No network call found.

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_CREDENTIAL

    hooks/action_gate.py, line 57

    (r"(curl|wget)\b.*(-d|--data|-T|--upload-file|-F)\b.*(\$|token|secret|key|password|\.env)",

    hooks/action_gate.py, line 59

    (r"(cat|head|tail|echo|printf)\b[^|]*(\.env|secret|token|api[_-]?key|password|id_rsa|credential)[^|]*\|\s*(curl|wget|nc)\b",

  • Agent instructions

    Serious

    instructions tell the agent to ignore earlier instructions.

    AGENT_IGNORE_INSTRUCTIONS

    hooks/README.md, line 78

    ignore prior instructions, forged system turns, secrecy or exfiltration

  • 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.

Get the full report on this tool, £49

Note

Hygiene check of commit 6424ccb8a72e. requests shell access. The manifest names this permission. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.

Date and source

Date checked:

View source

github.com

Commit graded: 6424ccb8a72ecfa8291d25e931732f3af2ba30d8

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