Security Audit

implementing-llms-litgpt

github.com/davila7/claude-code-templates

AI SkillCommit 458b11867eae

TRUSTED

Scanned 11 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

implementing-llms-litgpt received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 1 medium, and 2 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Unpinned Dependencies in Manifest.

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

98%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Security Findings3

Severity	Finding	Layer	Location
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
LOW	Unpinned Dependencies in Manifest The skill's manifest lists dependencies ('litgpt', 'torch', 'transformers') without specific version pinning. This practice can lead to unexpected behavior, compatibility issues, or introduce security vulnerabilities if a future version of these libraries contains breaking changes or malicious code. While these are well-known libraries, unpinned dependencies increase the risk of supply chain attacks if a malicious version were to be published. Pin all dependencies to specific versions (e.g., 'litgpt==0.1.0') or use version ranges with upper bounds (e.g., 'litgpt>=0.1.0,<0.2.0') to ensure consistent and secure environments, mitigating potential supply chain risks.	Static	manifest.json:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d9ce9833099dad68.svg)](https://skillshield.io/report/d9ce9833099dad68)