Versioned security assessment

Report ID: SA-E9E47122

7/4/2026, 1:34:12 PM

memory-bank security assessment v7

Skill Security Certification Report

Audit History
Audit model: codex Latest published report
Skill name
memory-bank
Version
v7
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

1 confirmed security finding requires 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 analyzer flagged Markdown fence delimiters as Ruby or shell backtick execution and flagged a progress template heading as network reconnaissance. Review found those static hits to be false positives, with only benign documentation examples and a local directory creation example. The remaining concern is semantic: persistent memory files can carry prompt-injection content if they are treated as authoritative instructions.

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

1 Files scanned · 283 Lines analyzed

1 item 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.

Not recorded by this audit

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 19 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Medium
SKILL.md:9SKILL.md:87-97SKILL.md:121-127
Persistent Context Can Carry Prompt Injection
The skill instructs the agent to read all memory bank files at every task start and rely on them for continuity. If repository documentation is untrusted, malicious content in those files could influence later sessions.
The instructions explicitly make memory-bank files persistent session context. The risk depends on who can edit those files, so this is a real contextual risk but not direct malware.

Remediation

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

  1. FIX-001
    Medium
    Persistent memory files may become a prompt-injection channel.
    State that memory-bank files are project context only, and that system, developer, and current user instructions take priority over stored notes.
  2. FIX-002
    Low
    The bash setup example can trigger command-execution scanners.
    Label the mkdir command as optional local setup, and require normal user approval before running any shell command.

Expert evidence

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

Artifact subject

Marketplace commit
e9e4712298ed071d92417a41714be123eb8364fa
Content hash
e478d8f1ee0c8564051e47d412ef33c1a923b1cc70c0db4574e1a46c3a83e2c8
Tree hash
cf412ff21e80d48d0992fe0c3211a8f26746dd5c3241bbdad3ec019bbe048aeb
Skill path
skills/0xkynz/memory-bank
Audit payload hash
4fd2461267343f824ac605f5bb24d470

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