Security Audit
performance-testing-review-multi-agent-review
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
performance-testing-review-multi-agent-review 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, 0 high, 1 medium, and 0 low severity. Key findings include Skill designed to operate on broad file system and network resources.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill designed to operate on broad file system and network resources The skill's input parameters explicitly state support for 'File paths' and 'Git repositories' as targets for review. This implies the skill is designed to access and process arbitrary local files and clone remote Git repositories. If the skill is deployed in an environment without strict sandboxing or access controls, this broad access could be exploited to read sensitive local files or interact with arbitrary remote repositories, potentially leading to data exfiltration or unauthorized code execution. Ensure the skill is executed within a strictly sandboxed environment with minimal necessary file system and network permissions. Implement robust input validation to restrict file paths to allowed directories or types. For Git repositories, consider using a secure cloning mechanism that validates URLs and prevents arbitrary command execution. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/d7cf66581f0423b4)
Powered by SkillShield