Security Audit

mattpocock/skills:skills/misc/git-guardrails-claude-code

github.com/mattpocock/skills

AI SkillCommit 9603c1cc8118

CRITICAL

Scanned 9 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

mattpocock/skills:skills/misc/git-guardrails-claude-code 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 9 findings: 4 critical, 5 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Command Injection in Git Guardrails Hook Script.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.

Last analyzed on July 17, 2026 (commit 9603c1cc). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

Static Code Analysis

40%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

4 findings

Filesystem Write

8 findings

Shell Execution

5 findings

Dynamic Code

1 finding

Excessive Permissions

8 findings

Security Findings9

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/misc/git-guardrails-claude-code/SKILL.md:20
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/misc/git-guardrails-claude-code/SKILL.md:29
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/misc/git-guardrails-claude-code/SKILL.md:57
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/misc/git-guardrails-claude-code/SKILL.md:68
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/misc/git-guardrails-claude-code/SKILL.md:20
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/misc/git-guardrails-claude-code/SKILL.md:29
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/misc/git-guardrails-claude-code/SKILL.md:57
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/misc/git-guardrails-claude-code/SKILL.md:68
HIGH	Command Injection in Git Guardrails Hook Script The hook script `scripts/block-dangerous-git.sh` parses the tool input command using `jq` and then passes the unescaped command variable `$COMMAND` directly into `echo` and `grep -qE`. If an attacker crafts a command containing shell metacharacters or command substitution syntax (e.g., backticks or `$()`), it can lead to arbitrary command execution or bypasses when evaluated by the shell or grep. Avoid passing raw command strings to external shells or grep patterns without strict sanitization. Use double quotes consistently, or implement the matching logic in a safer language like Python or Node.js where regex matching does not risk shell expansion.	LLM	scripts/block-dangerous-git.sh:17

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4b1e805c84747f6b.svg)](https://skillshield.io/report/4b1e805c84747f6b)