Trust Assessment
server-management received a trust score of 84/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Excessive permissions declared for informational skill.
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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Excessive permissions declared for informational skill The skill 'server-management' is described as a rubric that teaches principles and does not execute commands. However, its manifest declares broad permissions including `Bash`, `Write`, `Edit`, `Glob`, and `Grep`. These permissions are unnecessary for a purely informational skill and introduce an elevated risk if the skill were to be compromised or misused. An agent using this skill would have the capability to perform these actions, even if the skill's current content does not explicitly instruct them. Restrict `allowed-tools` to the absolute minimum required for the skill's functionality. For a purely informational skill, no permissions or only `Read` (if it needs to read internal data) should be declared. Remove `Bash`, `Write`, `Edit`, `Glob`, and `Grep`. | LLM | manifest | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/eb00f37a285af995)
Powered by SkillShield