Security Audit

claude-command-converter

github.com/dceoy/speckit-agent-skills

AI SkillCommit a934d48ecf66

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

claude-command-converter 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, 1 high, 0 medium, and 0 low severity. Key findings include Skill requires broad file system access, potential for data exfiltration.

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 April 1, 2026 (commit a934d48e). 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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill requires broad file system access, potential for data exfiltration The skill description indicates it will read a 'Source command file path' provided as input and create new directories. If the input file path is not strictly validated and sandboxed, a malicious user could provide paths to sensitive files outside the intended scope (e.g., `/etc/passwd`, `~/.ssh/id_rsa`), leading to data exfiltration. The skill also implies broader repository access for 'Repo context'. This constitutes excessive permissions for a user-controlled input. Implement strict input validation for all file paths to ensure they are within an allowed, sandboxed directory. Avoid allowing absolute paths or paths that traverse outside the intended skill directory. Ensure the underlying execution environment for the skill operates with the principle of least privilege, limiting file system access to only what is absolutely necessary for its function. Consider using a virtual file system or chroot jail if possible.	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/066ee5542d9de40e.svg)](https://skillshield.io/report/066ee5542d9de40e)