Security Audit

finishing-a-development-branch

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned 3 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

finishing-a-development-branch 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 Potential Command Injection via gh pr create arguments.

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 20, 2026 (commit e36d6fd3). 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

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via gh pr create arguments The skill instructs the agent to create a GitHub Pull Request using the `gh pr create` command. The `--title` and `--body` arguments are populated with placeholders (`<title>`, `<2-3 bullets of what changed>`, `<verification steps>`). If the agent populates these placeholders directly from untrusted user input without proper sanitization or escaping, a malicious user could inject shell commands into the PR title or body. These injected commands would then be executed by the underlying shell when the `gh pr create` command is run. For example, a title like `"; rm -rf /; #` could lead to arbitrary command execution on the host system. The agent should ensure that any user-provided input used to populate the `--title` or `--body` arguments for `gh pr create` is thoroughly sanitized and escaped to prevent shell metacharacters from being interpreted as commands. Using a dedicated GitHub API client or library function that handles argument escaping internally is preferred over direct shell command execution with string interpolation. If shell execution is necessary, use a method that passes arguments safely (e.g., `subprocess.run` with `shell=False` and arguments as a list) or explicitly escape all user-controlled input before passing it to the shell.	LLM	SKILL.md:91

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e456947ae82a1eda.svg)](https://skillshield.io/report/e456947ae82a1eda)