Versioned security assessment

Report ID: SA-F490BF9F

5/25/2026, 12:33:38 PM

visual-reviewer security assessment v1

Skill Security Certification Report

Audit History
Audit model: claude Historical report
Skill name
visual-reviewer
Version
v1
Maintainer
Barry-Liu-888
Coverage
5 Files scanned · 849 Lines analyzed
Policy version
Unavailable

Highest confirmed finding severity

Medium

3 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 visual-reviewer skill captures screenshots of user screens and enumerates running processes for window targeting. After evaluating all 64 static findings: all are FALSE POSITIVES. The external_commands patterns are documentation code examples in SKILL.md and legitimate screenshot scripts. The weak cryptographic algorithm flags are misidentifications of comments and Chinese text. The high entropy flags are caused by bilingual Chinese/English content. The skill has a legitimate purpose of visual quality review with no evidence of data exfiltration or malicious intent. However, screen capture and process enumeration are inherently sensitive operations that require user awareness.

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

5 Files scanned · 849 Lines analyzed

4 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.

Observed in 1 evidence location

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 6 evidence locations

Capability review items (1)
Low
High entropy in bilingual markdown files
Static analyzer flagged high entropy (6.26-6.78 bits) in SKILL.md and visual_checklist.md. This is caused by the bilingual Chinese and English text content, not by obfuscation or encoded payloads.

Risk findings

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

Confirmed security concerns (3)

RISK-001 Medium
Screen capture capability via Python script
The skill executes a Python script that captures screenshots of windows, active windows, screen regions, or full screen. This is the core functionality of the skill and is necessary for visual review. Screenshots are saved locally to disk and analyzed by the AI. No exfiltration mechanism was found.
RISK-002 Medium
Window and process enumeration
The skill enumerates visible windows and running processes to target specific application windows for screenshots. This is needed to capture the correct window by title or process name.
RISK-003 Medium
Auto-trigger instructions in skill definition
SKILL.md contains instructions for the AI to auto-trigger after any visual output is produced. While this is common for workflow automation skills, it instructs the AI to act without explicit user request. The actions taken (screenshot and visual analysis) match the stated purpose.

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: claude

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

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

Audit attestation: not_attestable