improve-codebase-architecture

Name: skills/improve-codebase-architecture
Author: mattpocock

Share on X Share on LinkedIn Share on Bluesky

70High

The skill lacks defined tool constraints and mandates opaque, unverified external dependencies, creating an insecure execution chain that prevents proper security auditing and risk assessment.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/29/2026

Content InjectionPerceptionclean

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlAction1 finding

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

Skill Info

Namemattpocock/skills/improve-codebase-architecture

Registrygithub

Version43ea0884b07a

PURLpkg:github/mattpocock/skills@43ea0884b07a?skill=improve-codebase-architecture

Stars150,476

Installs342,400

Source

Repository ↗SKILL.md ↗

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.

GitHub

342,400 installs

Skills.shDocs

npx skills add https://github.com/mattpocock/skills

Assessments (3)

AI Agent Traps ↗

Forced sub-agent orchestrationhighsub agent spawningAML.T0053AML.T0051.001LLM06:2025

The skill mandates the use of multiple external skills (/codebase-design, /grilling, /domain-modeling) without verifying their existence or safety, creating a complex, opaque execution chain. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]

80% confidence

run the /grilling skill to walk the design tree... run the /domain-modeling skill to keep the domain model current

Missing allowed-tools declarationlowunauthorized tool use

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence

Missing usage exampleslowpolicy violation

Skill body contains no code blocks or usage examples, making it harder for users to evaluate.

100% confidence

Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "HTML-REPORT.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence

[HTML-REPORT.md](HTML-REPORT.md)

Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Version History (2)

43ea0884b07acurrent70High6/29/2026 6eeb81b5fcfe15Low6/20/2026

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/mattpocock/skills/improve-codebase-architecture.svg)](https://mondoo.com/ai-agent-security/skills/github/mattpocock/skills/improve-codebase-architecture)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/mattpocock/skills/improve-codebase-architecture"><img src="https://mondoo.com/ai-agent-security/api/badge/github/mattpocock/skills/improve-codebase-architecture.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/mattpocock/skills/improve-codebase-architecture.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow