Security Audit

gracefullight/stock-checker:.agent/skills/trading-analysis

github.com/gracefullight/stock-checker

AI SkillCommit 4a711df68035

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

gracefullight/stock-checker:.agent/skills/trading-analysis 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, 0 high, 1 medium, and 0 low severity. Key findings include Potential Prompt Injection via User-Controlled Inputs to Internal LLM.

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 24, 2026 (commit 4a711df6). 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

93%

Behavioral Risk Signals

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Potential Prompt Injection via User-Controlled Inputs to Internal LLM The skill description indicates that user-provided inputs such as `client_name` and `report_title` are used in conjunction with 'Claude AI' for market analysis and intelligence. If these inputs are directly incorporated into prompts sent to the Claude API without proper sanitization or escaping, a malicious user could inject instructions into the internal LLM. This could lead to the LLM generating unintended content, revealing internal system prompts, or deviating from its intended analytical function. Implement robust input sanitization and escaping for all user-provided strings (`symbol`, `client_name`, `report_title`, `period`) before they are incorporated into prompts sent to the Claude AI model. Consider using templating engines or structured input methods for LLM calls to clearly separate user input from system instructions. Validate inputs against expected formats and content.	LLM	SKILL.md:26

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0be0c9334c7167bf.svg)](https://skillshield.io/report/0be0c9334c7167bf)