ModelsAtlas
Explore
Atlas / Skills / alirezarezvani / Brand Guidelines

Brand GuidelinesBLOCK

skills/alirezarezvani/brand-guidelines
Agent skill by alirezarezvani · agent plugins · agent skills · agentic ai · Audited 2026-10-06
⚑ Report / re-scanSource ↗

380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commerc

Verdict
BLOCK
Grade
D
Trust score
69 /100
Version
—
Hosts
—
License
MIT
Stars
27,775
01

Overview

380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commerc

Read from source at commit b228be08e8bdOBSERVED · 2026-10-06
02

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (7)

HIGHPrompt injection · review.misleading_scope · CWE-94, CWE-1427
<listing:description>
Covers color systems, typography, logo rules, imagery guidelines, and tone matrix for any brand
Why it matters. The package description promises brand guidelines content (colors, typography, logos, imagery, tone) but the actual files are an Apache License and a license compatibility matrix, which is a significant scope mismatch.
Fix. rewrite it so the instruction says plainly what it does, and asks the user before it acts
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.codex/skills/a11y-audit
.codex/skills/a11y-audit
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.codex/skills/ab-test-setup
.codex/skills/ab-test-setup
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.codex/skills/ad-creative
.codex/skills/ad-creative
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.codex/skills/adversarial-reviewer
.codex/skills/adversarial-reviewer
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.codex/skills/aeo
.codex/skills/aeo
Why it matters. link not followed
MEDIUMInventory / provenance · skill.no_skill_md · CWE-1104
Why it matters. no SKILL.md at the audited path
Fix. a skill without its instruction file cannot be reviewed as one

Gates applied: no_behavioural_pass.

Audited 2026-10-06 · audit v0.4.1 · source sha b228be08e8bdfull audit observations/trust-audit/skill/alirezarezvani__brand-guidelines.json · Report an issue / request a re-scan
03

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-06b228be08e8bdBLOCKD69first audit
04

Questions

What does the Brand Guidelines skill do?

380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commerc

Is Brand Guidelines safe to install?

No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.

What can Brand Guidelines access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (b228be08e8bd), read on 2026-10-06. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement