Security Audit

Petersobhy/ai-toolkit:skills/sonarcloud-scan

github.com/Petersobhy/ai-toolkit

AI SkillCommit 5346c5f74659

CRITICAL

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Petersobhy/ai-toolkit:skills/sonarcloud-scan received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 5 findings: 2 critical, 2 high, 1 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Command Injection via Unquoted Shell Arguments.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on September 12, 2026 (commit 5346c5f7). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

40%

Static Code Analysis

70%

Dependency Graph

100%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

4 findings

Shell Execution

3 findings

Dynamic Code

1 finding

Excessive Permissions

4 findings

Security Findings5

Severity	Finding	Layer	Location
CRITICAL	File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	skills/sonarcloud-scan/SKILL.md:31
CRITICAL	File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality.	Manifest	skills/sonarcloud-scan/SKILL.md:61
HIGH	Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	skills/sonarcloud-scan/SKILL.md:31
HIGH	Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared.	Static	skills/sonarcloud-scan/SKILL.md:61
MEDIUM	Potential Command Injection via Unquoted Shell Arguments The skill instructions guide the LLM to execute a bash command using user-provided arguments (`<severity>` and `<repo>`) without wrapping them in quotes. If a user provides a repository name or severity containing shell metacharacters (e.g., `; malicious_command`), it could result in arbitrary command execution within the host environment. Update the command template in SKILL.md to wrap the arguments in single quotes (e.g., `--severity '<severity>' --repo '<repo>'`) and explicitly instruct the LLM to sanitize or escape shell metacharacters in user-controlled inputs before executing the command.	LLM	SKILL.md:54

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/212d484cdbbbd1e1.svg)](https://skillshield.io/report/212d484cdbbbd1e1)