Versioned security assessment

Report ID: SA-69D69334

7/6/2026, 7:55:03 AM

Command Development security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
Command Development
Version
v7
Maintainer
anthropics
Source
github.com/anthropics/claude-code/tree/main/plugins/plugin-dev/skills/command-development
Coverage
11 Files scanned · 7,237 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

2 confirmed security findings require attention.

Installation context

Historical evidence

This report may not describe the currently installable artifact. Open the current Skill page for install guidance.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

The static findings are predominantly false positives from Markdown documentation and slash command examples, not executable skill code. No prompt injection attempt, credential exfiltration, or install-time execution behavior was found. The main residual risk is instructional: some examples show broad Bash permissions and direct shell interpolation of user arguments.

Report position

Historical report

Open audit history before using this report to install.

Audit attestation

Not attestable

The required immutable binding is incomplete.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

11 Files scanned · 7,237 Lines analyzed

2 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Binding unavailable

  2. Artifact

    Identity incomplete

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 8 evidence locations

Filesystem access

May read or write local files.

Observed in 25 evidence locations

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 347 evidence locations

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (2)

RISK-001 Medium
examples/plugin-commands.md:61references/plugin-features-reference.md:129SKILL.md:608
Broad Bash Permissions in Examples
Several examples use unrestricted or lightly restricted Bash tool access, including Bash(*). If users copy these examples unchanged, generated commands may receive broader shell permissions than needed.
The cited lines directly show broad Bash permissions in command examples. The skill also advises narrower filters elsewhere, so this is an instructional hardening issue rather than malicious intent.
RISK-002 Medium
examples/simple-commands.md:100examples/plugin-commands.md:35SKILL.md:461
Unvalidated Shell Argument Interpolation in Examples
Some command examples place positional arguments directly inside shell commands. If copied without quoting or validation, user-controlled arguments could alter the shell command that runs.
The examples visibly pass $1 to shell commands. Legitimate workflows may need arguments, but command authors should validate and quote inputs before reuse.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    Medium
    Examples use broad Bash permissions such as Bash(*).
    Prefer narrow command filters in examples, such as Bash(git:*) or Bash(node:*), and mark unrestricted Bash examples as exceptional.
  2. FIX-002
    Medium
    Some shell examples pass positional arguments directly to commands.
    Add validation and quoting guidance beside examples that use $1, $2, or $ARGUMENTS in shell commands.
  3. FIX-003
    Low
    Documentation includes many shell examples that can be copied into real commands.
    Add a short safety checklist before command examples that covers least privilege, input validation, and destructive command review.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
Unavailable
Content hash
Unavailable
Tree hash
Unavailable
Skill path
Unavailable
Audit payload hash
Unavailable

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

JSON report CITATION.cff SARIF 2.1.0 Signed installation manifest

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: not_attestable