Security Audit
rag-implementation
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
rag-implementation 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 Potential data transmission to third-party services.
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 | Potential data transmission to third-party services The provided code snippets demonstrate the use of `OpenAIEmbeddings` and `OpenAI` for processing documents and queries, and `Pinecone` and `Weaviate` for vector storage. These services typically involve sending user data (documents, text chunks, queries) to external APIs or managed databases. If the documents loaded via `DirectoryLoader` contain sensitive or proprietary information, this data will be transmitted to these third-party services. While the 'Safety' section in the skill's description advises to 'Redact sensitive data and enforce access controls', the example code does not implement these measures, potentially leading to unintended data exposure if used directly with sensitive data. Implement robust data redaction, anonymization, or access control mechanisms before sending any sensitive data to third-party services. Ensure users are fully aware of the data privacy policies and security practices of all integrated external services (e.g., OpenAI, Pinecone, Weaviate). For highly sensitive data, consider using local or self-hosted alternatives for embedding models and vector databases. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/8803f1718303e993)
Powered by SkillShield