Security Audit

garrytan/gstack:openclaw/skills/gstack-openclaw-retro

github.com/garrytan/gstack

AI SkillCommit dbd7aee5b6b5

CAUTION

Scanned 18 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

garrytan/gstack:openclaw/skills/gstack-openclaw-retro received a trust score of 55/100, 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 Potential Command Injection via Unsanitized User Input.

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 9, 2026 (commit dbd7aee5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

85%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via Unsanitized User Input The skill instructs the LLM to 'Parse the argument to determine the time window' (line 20) and then use this parsed value as a direct placeholder '<window>' in multiple 'git log' commands (e.g., line 34). Without explicit instructions for strict validation and sanitization of the user-provided time window argument, a malicious user could inject arbitrary shell commands. For example, if the user input for the time window is '24h"; rm -rf /; echo "', it could lead to the execution of 'rm -rf /' within the skill's execution environment, as the LLM might directly interpolate the unsanitized input into the shell command. Instruct the LLM to strictly validate and sanitize the user-provided time window argument. Ensure that only expected patterns (e.g., '24h', '7d', 'compare') are accepted. The argument should then be programmatically converted into a safe `--since` value (e.g., `--since="24 hours ago"` or a specific date string) rather than directly interpolating the raw user input. This prevents arbitrary command execution by ensuring the input cannot break out of the intended argument structure.	Static	SKILL.md:34

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/8aee9975b8445d42.svg)](https://skillshield.io/report/8aee9975b8445d42)