Versioned security assessment

Report ID: SA-4E00F3ED

6/27/2026, 12:37:40 PM

memory-bank security assessment v4

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
memory-bank
Version
v4
Maintainer
0xkynz
Source
github.com/0xkynz/codekit/tree/main/templates/skills/memory-bank
Coverage
1 Files scanned · 283 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 external-command findings are mostly false positives from Markdown fences, and the weak-crypto and reconnaissance detections have no supporting code evidence. The meaningful risks are semantic: the skill is always applied, directs broad trust in persistent Memory Bank files, and expects filesystem writes.

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

1 Files scanned · 283 Lines analyzed

3 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.

Not recorded by this audit

Filesystem access

May read or write local files.

Observed in 3 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 1 evidence location

Capability review items (1)
Medium
SKILL.md:76-81SKILL.md:101-117SKILL.md:131-135
Expected Filesystem Modification
The workflow directs the assistant to create and update project documentation files. This is legitimate for the skill, but users should expect repository changes when it is active.
The file creation and update behavior is directly described. It is not malicious, but it changes project files and therefore deserves a marketplace warning.

Risk findings

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

Confirmed security concerns (2)

RISK-001 Medium
SKILL.md:4-9SKILL.md:87-97SKILL.md:121-127
Always-On Persistent Memory Trust
The skill is configured for automatic application and instructs the assistant to rely entirely on Memory Bank files. If those files are stale or poisoned, future sessions may inherit unsafe instructions or incorrect project state.
The alwaysApply flag and mandatory memory-loading instructions are explicit. The risk depends on future Memory Bank content, so this is a medium semantic risk rather than confirmed malicious behavior.
RISK-002 Low
SKILL.md:15-34SKILL.md:147-270
Static Command Findings Are Mostly Markdown Fences
The reported Ruby backtick execution locations are Markdown code fences and documentation examples. No evidence found of Ruby execution, dynamic command construction, or automatic command execution.
The cited areas are fenced Markdown blocks or templates. The only actual shell command is a simple directory creation example at lines 133-135.

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 (1)
Low
SKILL.md:3SKILL.md:59SKILL.md:151SKILL.md:214SKILL.md:224SKILL.md:259
Weak-Crypto And Reconnaissance Detections Are False Positives
No evidence found of cryptographic code or network reconnaissance behavior. The cited lines contain prose, Markdown filenames, placeholders, or checklist text.
The source is documentation-only Markdown with no cryptographic API calls or networking commands. The flagged lines do not implement executable behavior.

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