Versioned security assessment

Report ID: SA-1F11D54D

6/29/2026, 11:15:02 AM

project-creator security assessment v6

Skill Security Certification Report

Audit History

Audit model: codex Historical report

Skill name: project-creator
Version: v6
Maintainer: Daron Vener
Source: github.com/DaronVee/ccgg-project-creator-skill/tree/master/project-creator/
Coverage: 10 Files scanned · 1,941 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.

AI review found that most static findings are false positives from markdown examples, relative documentation paths, repository metadata, and ordinary words such as PARENT SYSTEM INTEGRATION. No evidence of malicious intent, prompt injection, credential access, obfuscation, or network exfiltration was found. The remaining risk is medium because the skill intentionally writes local project files and its validation scripts construct paths from an unvalidated project name.

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

10 Files scanned · 1,941 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.

Observed in 2 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.

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

scripts/validate_project.py:27-28 scripts/validate_project.sh:11-12

Unvalidated Project Name Used In Local Paths

Verdict: TRUE_POSITIVE. The Python and Bash validators build project and index paths directly from the project name. A value containing path traversal segments could make the validators inspect files outside the intended CCGG incubator and index folders. The impact is limited because the validators mainly read files and print status, but the scripts do not enforce the hyphen-case constraint documented in SKILL.md.

The vulnerable path construction is directly visible in both validators. Confidence is not higher because the scripts are local validation helpers and do not print full file contents.

RISK-002 Medium

SKILL.md:172-178 SKILL.md:402-407

Intentional Filesystem Modification Workflow

Verdict: TRUE_POSITIVE with legitimate purpose. The skill instructs the assistant to create project folders, write CLAUDE.md and README.md files, generate optional phase trackers, and add operations log entries. This is expected for a project scaffolding skill, but marketplace users need a warning because it changes local workspace files.

The file creation and logging workflow is clearly documented as intended behavior. It is a medium marketplace risk because the behavior is broad but not malicious.

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:421-423 SKILL.md:566-568 scripts/README.md:10-12

Markdown Command Examples Flagged As Execution

Verdict: FALSE_POSITIVE. Most external command hits are fenced markdown examples or usage snippets, not hidden code paths. The commands are visible validation and logging examples for the user to run manually.

The cited lines are documentation blocks and visible command examples. No concealed command execution or dynamic shell construction was found in those markdown sections.

Low

SKILL.md:583-585 references/mechanism_specifications.md:11-13 templates/README.md:7-9

Sensitive And Crypto Keyword Matches Are Terminology Collisions

Verdict: FALSE_POSITIVE. The critical sensitive matches are caused by project terminology such as PARENT SYSTEM INTEGRATION, and weak crypto matches are caused by markdown filenames or ordinary documentation text. No Windows SAM database access or cryptographic implementation was found.

The surrounding text shows business process terminology and template documentation. There is no evidence of credential database access or weak cryptographic algorithm use.

Low

SKILL.md:14

Repository URL Flagged As Network Risk

Verdict: FALSE_POSITIVE. The hardcoded URL in SKILL.md is repository metadata, not code that performs a network request. No fetch, curl, webhook, or exfiltration behavior was found in the reviewed files.

The URL appears in frontmatter metadata only. No network-capable implementation was identified during contextual review.

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