Security Audit
nvidia/skillspector:tests/fixtures/mcp_overprivileged_skill
github.com/nvidia/skillspectorTrust Assessment
nvidia/skillspector:tests/fixtures/mcp_overprivileged_skill 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 Excessive Permissions Requested.
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 June 4, 2026 (commit 2eb84478). 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 | Excessive Permissions Requested The skill requests highly privileged permissions ('bash', 'network', 'write', and '*') in its manifest, which are completely unnecessary for a simple file reader utility. This violates the principle of least privilege and significantly increases the impact of any potential compromise or prompt injection attack. Restrict the permissions in the manifest to only the minimum required for the skill's functionality (e.g., 'read' only) and remove 'bash', 'network', 'write', and '*'. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/c037a88d0276e340)
Powered by SkillShield