Security Audit

ultimatebos/agent-shield:root

github.com/ultimatebos/agent-shield

AI SkillCommit 6558e62f73c0

TRUSTED

Scanned 18 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

ultimatebos/agent-shield:root received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Cryptocurrency Promotion and Financial Solicitation in Skill.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on July 7, 2026 (commit 6558e62f). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Security Findings1

Severity	Finding	Layer	Location
HIGH	Cryptocurrency Promotion and Financial Solicitation in Skill The skill contains promotional material, social engineering prompts, and direct links to purchase a cryptocurrency token ($CHITIN on Solana/pump.fun). AI agent skills should not solicit financial transactions, promote speculative tokens, or instruct the host LLM to post promotional messages on social platforms (e.g., Moltbook). Remove all cryptocurrency token addresses, trading links, and social media posting instructions from the skill documentation.	LLM	SKILL.md:51

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2d48a9a65c70201b.svg)](https://skillshield.io/report/2d48a9a65c70201b)