Versioned security assessment

Report ID: SA-814B442B

6/28/2026, 10:27:43 AM

Command Development security assessment v5

Skill Security Certification Report

Audit History

Audit model: codex Historical report

Skill name: Command Development
Version: v5
Maintainer: anthropics
Source: github.com/anthropics/claude-plugins-official/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.

Static analysis reported many command execution, filesystem, network, and cryptography patterns, but review shows they are primarily Markdown documentation and examples for Claude Code slash commands. No prompt injection attempt or confirmed malicious intent was found. The skill should publish with a medium warning because it teaches Bash-enabled commands, file references, and tool permissions that can be risky if copied without review.

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.

Source

Binding unavailable
Artifact

Identity incomplete
Audit

Complete
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 2 evidence locations

Filesystem access

May read or write local files.

Observed in 4 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 4 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium

SKILL.md:128-143 README.md:145-146 examples/simple-commands.md:9-15

Bash-Enabled Slash Command Guidance

TRUE_POSITIVE for capability risk, not malicious intent. The skill documents allowed-tools with Bash access and command output interpolation, which can execute shell commands if users create commands from these examples.

The cited lines explicitly describe Bash tool access or Bash execution syntax. The context is legitimate documentation, so the confidence is high for capability risk but not for malicious behavior.

RISK-002 Medium

README.md:132-146 SKILL.md:62-64 SKILL.md:271-288

File Reference and Personal Command Path Guidance

TRUE_POSITIVE for capability risk. The skill explains home-directory command locations and file-reference syntax, which is expected for Claude Code commands but can read sensitive files if command authors use broad paths or untrusted arguments.

The evidence directly shows personal command paths and file inclusion behavior. It is a normal feature, but the security impact depends on how generated commands are used.

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.

Static false positives ignored (3)

Low

README.md:117-121 examples/simple-commands.md:11-15 references/frontmatter-reference.md:9-15

Weak Cryptography Static Detections Are False Positives

FALSE_POSITIVE. Representative flagged areas are Markdown fences, command descriptions, and frontmatter examples, not cryptographic API usage or weak hash implementation.

The reviewed lines are documentation examples and do not call cryptographic functions. The scanner likely matched Markdown or abbreviated text patterns out of context.

Low

references/documentation-patterns.md:579-582

Sensitive Windows SAM Static Detection Is False Positive

FALSE_POSITIVE. The flagged line is a documentation heading for security considerations inside maintenance notes, with no Windows SAM database access or credential extraction behavior.

The cited context discusses validating inputs and avoiding credentials in command files. No sensitive Windows database path or access pattern appears at the flagged location.

Low

references/marketplace-considerations.md:635-638 references/documentation-patterns.md:684-685

Placeholder Network URLs in Documentation

FALSE_POSITIVE for network activity. The URLs are support and documentation placeholders in marketplace guidance, not executable fetch calls or data exfiltration endpoints.

The evidence shows example documentation links only. There is no code path that sends data to those URLs.

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