Versioned security assessment

Report ID: SA-B6ACA886

6/28/2026, 9:16:15 AM

planning-with-files security assessment v6

Skill Security Certification Report

Audit History
Audit model: codex Historical report
Skill name
planning-with-files
Version
v6
Maintainer
AmmarCodes
Source
github.com/AmmarCodes/dotfiles/tree/master/opencode/skill/planning-with-files
Coverage
3 Files scanned · 531 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Low

1 confirmed security finding requires 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 command-execution patterns, weak-crypto indicators, a browser-storage reference, reconnaissance indicators, and one hardcoded URL. Manual review found these are markdown examples and documentation text, not executable code or instructions to exfiltrate data. The skill does encourage creating, reading, and editing local markdown files, so the main residual risk is expected filesystem use during workflow planning.

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

3 Files scanned · 531 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

    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.

Observed in 2 evidence locations

Filesystem access

May read or write local files.

Observed in 6 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 5 evidence locations

Risk findings

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

Confirmed security concerns (1)

RISK-001 Low
SKILL.md:14-17SKILL.md:21-27SKILL.md:120-138reference.md:87-94
Filesystem-Oriented Workflow Instructions
The skill intentionally asks the assistant to create, read, write, and edit local markdown files such as task_plan.md and notes.md. This is core functionality and not malicious, but users should expect filesystem changes in the working directory.
The source repeatedly instructs the assistant to use local markdown files for planning and notes. The behavior is explicit and legitimate for the skill purpose, with no evidence of unsafe file targets.

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:42-56examples.md:40-44examples.md:49-53examples.md:194-213reference.md:83-94
Documentation Examples Mistaken for Shell Execution
Static analysis flagged many fenced blocks as Ruby or shell backtick execution. Manual review shows they are human-readable workflow examples such as Read task_plan.md and Write notes.md, not executable scripts or command substitution.
The flagged text appears inside markdown documentation blocks and names assistant tool-like operations. No executable code file, shell invocation, or user-controlled command construction was found.
Low
reference.md:113-116
External URL Used as Source Citation
The only hardcoded URL is a citation to Manus context engineering documentation. It does not instruct the assistant to send data to the URL or make an automatic network request.
The URL is under a Source heading and is presented as reference material. There is no nearby credential access, upload instruction, or automated request logic.
Low
SKILL.md:1-3SKILL.md:62-67reference.md:1-11examples.md:132-136
Static Weak-Crypto and Browser-Storage Alerts Are Contextual False Positives
Weak-cryptography and browser-storage alerts come from prose and example planning notes, including markdown filename references and a dark mode example mentioning localStorage. No hashing implementation or sensitive browser data access is present.
The suspicious terms are embedded in markdown documentation and an illustrative UI planning example. I found no cryptographic operation, no credential handling, and no instruction to inspect real browser storage.

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