Security Audit
azure-resource-manager-cosmosdb-dotnet
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
azure-resource-manager-cosmosdb-dotnet 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 Example code demonstrates printing sensitive credentials.
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 | Example code demonstrates printing sensitive credentials The provided C# code examples in the 'Get Connection Information' section demonstrate how to retrieve Cosmos DB primary keys and connection strings. These examples then print the sensitive values directly to `Console.WriteLine()`. If an AI agent were to generate and execute code based on these examples, it could lead to the exfiltration of highly sensitive credentials through the agent's output logs or interface, posing a significant security risk. Advise against printing sensitive credentials directly to standard output. Instead, recommend secure storage, environment variables, or passing them securely to other components. For documentation, add a prominent warning about handling these outputs securely and suggest redaction or alternative secure logging mechanisms. | LLM | SKILL.md:124 |
Scan History
Embed Code
[](https://skillshield.io/report/30aadc4e8a19d8a1)
Powered by SkillShield