Security Audit

security-compliance-compliance-check

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned about 19 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

security-compliance-compliance-check 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 instructs LLM to open files based on conditions.

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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill instructs LLM to open files based on conditions The skill's instructions, located within the untrusted input, direct the host LLM to 'open' a file (`resources/implementation-playbook.md`) if certain conditions are met. This pattern creates a prompt injection vulnerability. An attacker could craft a prompt that satisfies the condition ('detailed examples are required') and then attempt to manipulate the file path to open arbitrary files on the system (e.g., `/etc/passwd`, `/app/secrets.txt`). This could lead to data exfiltration or further command injection if the underlying file access mechanism is not properly sandboxed or if the LLM interprets 'open' as a shell command. Implement strict validation and sanitization of file paths before any file access operations. Ensure the underlying file opening mechanism is sandboxed and only allows access to explicitly permitted files or directories. Avoid dynamic file path construction based on untrusted user input. Consider using a tool that returns file content rather than 'opening' it directly, and restrict its scope to known, safe files.	LLM	SKILL.md:25

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/57e5892ca56e39b8.svg)](https://skillshield.io/report/57e5892ca56e39b8)