Trust Assessment
graphql-architect received a trust score of 98/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 0 medium, and 1 low severity. Key findings include Implied Local File System Access.
The analysis covered 4 layers: dependency_graph, static_code_analysis, manifest_analysis, llm_behavioral_safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 3d5e297b). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| LOW | Implied Local File System Access The skill defines a 'Reference Guide' table that points to local markdown files (e.g., `references/schema-design.md`). This implies that the AI agent using this skill is expected to have the capability to read local files from the skill's directory structure. While this is a common pattern for including documentation, it indicates a requirement for file system access. If the agent's execution environment grants broad file system access, and if the mechanism for loading these references is not robust against path traversal or injection, it could potentially lead to unauthorized file reads. Ensure the AI agent's execution environment is properly sandboxed, limiting file system access only to explicitly allowed directories. If references are loaded dynamically, validate and sanitize all paths to prevent path traversal vulnerabilities. Consider embedding critical reference content directly into the skill definition if local file system access is not strictly necessary. | Unknown | SKILL.md:42 |
Scan History
Embed Code
[](https://skillshield.io/report/37434244b6e408b2)
Powered by SkillShield