Security Audit
network-engineer
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
network-engineer 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, 0 medium, and 0 low severity. Key findings include Skill instructs LLM to access external file.
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 | |
|---|---|---|---|---|
| INFO | Skill instructs LLM to access external file The skill explicitly instructs the host LLM to 'open' a file (`resources/implementation-playbook.md`). While this is a common pattern for skills to access internal documentation, it represents a directive to the LLM to incorporate content from an external source within the skill package. If the content of `resources/implementation-playbook.md` were to contain malicious instructions or data, this directive could lead to prompt injection or other security issues. The content of `resources/implementation-playbook.md` was not provided for analysis. Ensure that `resources/implementation-playbook.md` is thoroughly reviewed for any malicious content, prompt injection attempts, or sensitive information. If the LLM has a tool to 'open' files, ensure this tool is sandboxed and restricted to only access allowed paths within the skill's own package. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/d836975bc21be89f)
Powered by SkillShield