Trust Assessment
2d-games 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 '2d-games' is described as providing '2D game development principles' and its primary content is a markdown document (`SKILL.md`) containing only descriptive text. However, the manifest declares broad permissions including 'Write', 'Edit', 'Glob', and 'Grep' in addition to 'Read'. For a purely informational skill, these additional permissions are excessive and unnecessary. Granting more permissions than required increases the attack surface, as a compromised or maliciously prompted agent could potentially use these elevated privileges to perform unintended file system operations (e.g., modifying, deleting, or listing files) that are not related to the skill's stated purpose. Review the 'allowed-tools' in the skill's manifest. For a skill that only provides static information, only 'Read' permission should be necessary. Remove 'Write', 'Edit', 'Glob', and 'Grep' permissions unless a clear functional requirement for them is identified and documented. | LLM | SKILL.md:1 | |
| 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/cd8cf5e2319446e0)
Powered by SkillShield