Security Audit

affaan-m/everything-claude-code:.cursor/skills/verification-loop

github.com/affaan-m/everything-claude-code

AI SkillCommit db27ba1eb225

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

affaan-m/everything-claude-code:.cursor/skills/verification-loop received a trust score of 56/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill instructs LLM to search for and report sensitive credentials.

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 db27ba1e). 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%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill instructs LLM to search for and report sensitive credentials The skill explicitly instructs the LLM to execute `grep` commands to find potential API keys and secrets (e.g., patterns like `sk-` prefixes and `api_key` strings) within the project's TypeScript/JavaScript files. It then requires these findings to be included in a 'VERIFICATION REPORT' under the 'Security' section. If the LLM follows these instructions, it will exfiltrate sensitive credentials found in the codebase by outputting them in its response, leading to credential harvesting and data exfiltration. Remove the `grep` commands that search for specific secret patterns and the instruction to report 'Security issues' based on these findings. Instead, recommend using dedicated security scanning tools that are designed to handle secrets securely (e.g., by only reporting their presence without revealing the secret itself, or by integrating with secret management systems). If the goal is to ensure secrets are not hardcoded, the LLM should be instructed to verify the absence of such patterns without reporting the actual values if found.	LLM	SKILL.md:59

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/16e36e2447705112.svg)](https://skillshield.io/report/16e36e2447705112)