Security Audit

web-design-guidelines

github.com/davila7/claude-code-templates

AI SkillCommit 458b11867eae

CAUTION

Scanned 12 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

web-design-guidelines received a trust score of 60/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, External content dictates LLM behavior, enabling prompt injection and arbitrary command execution.

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 February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

91%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings3

Severity	Finding	Layer	Location
CRITICAL	External content dictates LLM behavior, enabling prompt injection and arbitrary command execution The skill explicitly states it will 'Fetch fresh guidelines before each review' from an external URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) and then 'Apply all rules from the fetched guidelines'. This design allows an external, unverified source to directly influence and dictate the LLM's behavior. An attacker who gains control of the specified URL could inject arbitrary instructions (prompt injection), instruct the LLM to exfiltrate sensitive data (data exfiltration), or perform other malicious actions by leveraging the LLM's access to files and tools. This constitutes a severe supply chain risk, as the skill's runtime behavior is dependent on untrusted external content. Do not fetch and execute instructions or rules from external, unverified sources. All operational logic and rules should be self-contained within the skill package. If external data is absolutely necessary, it must be treated as untrusted data, parsed, and strictly validated against a predefined schema, never directly interpreted as instructions for the LLM. Consider using immutable, signed, and version-controlled resources if external dependencies are unavoidable.	LLM	SKILL.md:17
MEDIUM	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	cli-tool/components/mcps/devtools/figma-dev-mode.json:4
LOW	Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	cli-tool/components/mcps/devtools/jfrog.json:4

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ad2782505c0d6be2.svg)](https://skillshield.io/report/ad2782505c0d6be2)