Versioned security assessment

Report ID: SA-248952C8

7/1/2026, 3:23:27 AM

skill-creator security assessment v2

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
skill-creator
Version
v2
Maintainer
ZhanlinCui
Source
github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/skill-creator
Coverage
6 Files scanned · 978 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 high-risk markers, but review found them to be Markdown backticks, placeholder text, and validation strings. No real shell execution, cryptographic code, network access, secret access, or prompt injection was found. The real risks are local filesystem writes during scaffolding and packaging every file under a selected skill directory.

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

6 Files scanned · 978 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.

Observed in 3 evidence locations

Network access

May connect to external services.

Not recorded by this audit

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.

Not recorded by this audit

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
scripts/init_skill.py:206-215scripts/init_skill.py:228-258scripts/init_skill.py:287-288
Unvalidated Skill Name and Output Path Writes
The initializer builds a target directory from CLI arguments and writes SKILL.md plus example resources there. The script does not validate skill_name before composing the path, so careless agent use could create files outside the intended location.
The file writes are direct and user-controlled through CLI arguments. The behavior is legitimate scaffolding, but missing name validation creates a real filesystem safety concern.
RISK-002 Medium
scripts/package_skill.py:68-74
Skill Packaging Archives All Files Recursively
The packager walks the whole skill directory and adds every file to the .skill archive. This can accidentally include secrets, large files, generated output, or symlinked files if they are present in the skill folder.
The recursive archive behavior is explicit in the code and has no exclusion list. It is normal for a packager, but it creates a clear accidental data exposure risk.

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
SKILL.md:266-268SKILL.md:324-331references/workflows.md:7-15references/output-patterns.md:11-29scripts/init_skill.py:72-76
Static Command Execution Findings Are Markdown False Positives
The reported Ruby or shell backtick locations are Markdown fences, inline code examples, or template text. No evidence found of subprocess, os.system, eval, or shell command execution in the executable Python files.
The cited text is documentation or static template content. The reviewed scripts do not contain APIs that execute external commands.
Low
SKILL.md:3scripts/init_skill.py:18-20scripts/quick_validate.py:42-56references/output-patterns.md:79-82
Static Crypto and Sensitive File Findings Are Token Matches
The weak cryptography and certificate/key detections come from words such as description, metadata, allowed-tools, and example asset names. No evidence found of MD5, DES, SHA1 use, certificate parsing, or bundled key material.
The locations contain ordinary documentation and validation strings, not cryptographic functions or key files. The semantic review found no related security behavior.
Low
scripts/quick_validate.py:27-39scripts/quick_validate.py:89-95SKILL.md:199-200
Static System Reconnaissance Findings Are Validation Messages
The reported reconnaissance locations are normal validation checks, examples, and documentation guidance. No evidence found of host enumeration, credential discovery, environment dumping, or network discovery behavior.
The cited code only parses SKILL.md and returns validation messages. There is no host or network reconnaissance logic.

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