Security Audit
cost-optimization
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
cost-optimization 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 LLM instructed to open local 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 | |
|---|---|---|---|---|
| MEDIUM | LLM instructed to open local file The skill explicitly instructs the LLM to 'open' a local file (`resources/implementation-playbook.md`). This is a prompt injection attempt as it tries to manipulate the LLM into performing a specific action (file access) that could lead to data exfiltration or execution of further hidden instructions if the file content is untrusted or sensitive. This also implies the LLM has file system access, which could be an excessive permission. Remove direct instructions for the LLM to access local files. Instead, the skill should describe *what* the file contains and *how* the user (or a tool) might use it, without instructing the LLM to perform the action itself. For example, 'Detailed examples can be found in `resources/implementation-playbook.md`.' | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/136030c97084634d)
Powered by SkillShield