Security Audit
shopify-automation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
shopify-automation 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 grants broad access via arbitrary Shopify GraphQL queries.
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 | |
|---|---|---|---|---|
| HIGH | Skill grants broad access via arbitrary Shopify GraphQL queries The skill exposes `SHOPIFY_GRAPH_QL_QUERY` and `SHOPIFY_BULK_QUERY_OPERATION` tools, allowing the agent to execute arbitrary GraphQL queries against the Shopify API. This grants extremely broad access to read, modify, or delete data within the Shopify store, limited only by the underlying Shopify app's permissions. A compromised or manipulated agent could leverage this to exfiltrate sensitive data (e.g., customer PII, order details) or perform unauthorized actions beyond the scope of more specific tools. The documentation explicitly states 'Call SHOPIFY_GRAPH_QL_QUERY with custom query', confirming its generic and powerful nature. Restrict the `SHOPIFY_GRAPH_QL_QUERY` and `SHOPIFY_BULK_QUERY_OPERATION` tools to a predefined set of safe, read-only queries, or remove them if their broad functionality is not strictly necessary. If they must remain, implement strict input validation and allow-listing of query types/fields to prevent arbitrary data access or mutation. Ensure the underlying Shopify app permissions are as granular and least-privileged as possible. | LLM | SKILL.md:140 |
Scan History
Embed Code
[](https://skillshield.io/report/a353f5a4cd49bef1)
Powered by SkillShield