Versioned security assessment

Report ID: SA-88A205C7

7/8/2026, 3:50:55 PM

skill-creator security assessment v4

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
skill-creator
Version
v4
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

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

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

The static command, sensitive-file, and reconnaissance alerts are mostly false positives from markdown backticks, template text, validation errors, and zip packaging. No prompt injection or data exfiltration intent was found. Two local filesystem risks remain in the helper scripts: unvalidated output names and unfiltered packaging.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

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

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  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.

Not recorded by this audit

Filesystem access

May read or write local files.

Observed in 2 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 40 evidence locations

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
scripts/init_skill.py:205-206scripts/init_skill.py:287-288
Unvalidated Skill Name Can Escape Target Directory
scripts/init_skill.py joins the user supplied skill name to the target path before creating files. A name containing path separators could write outside the intended output folder.
The script prints naming rules but does not enforce them before building skill_dir from argv. This is a direct local path traversal risk for untrusted input.
RISK-002 Medium
scripts/package_skill.py:70-74
Unfiltered Packaging May Include Unintended Files
scripts/package_skill.py recursively writes every file under the selected skill directory into the .skill archive. A dirty folder could publish secrets, caches, or unrelated files.
The code includes all regular files returned by rglob without denylist, allowlist, or symlink checks. The archive is intended for distribution.

Remediation

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

  1. FIX-001
    Medium
    Skill names are not validated before directory creation.
    Reject names that fail the documented hyphen-case pattern, contain path separators, or resolve outside the requested output directory.
  2. FIX-002
    Medium
    The packager archives every file under the skill directory.
    Add a default denylist for secrets, hidden VCS folders, caches, generated archives, and symlinks before writing the .skill file.

Expert evidence

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

Artifact subject

Marketplace commit
88a205c7f635a966e31156313b590d59007c5caa
Content hash
b2e3d83f60425c2d0b9d4162efb8f9aa322b45843497340f2289f42be422801c
Tree hash
46371a04ec6884c357bc729716f303238a4a3c1b6f513fec5af35ddbc4b9d440
Skill path
skills/zhanlincui/skill-creator
Audit payload hash
2ed2c4f1c37f65f6117a37d313697b12

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 Source

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

Audit attestation: not_attestable