Trust Assessment
figma received a trust score of 75/100, 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, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Potential Local File Access via Malicious `localhost` URL.
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 | |
|---|---|---|---|---|
| HIGH | Potential Local File Access via Malicious `localhost` URL The skill instructs the agent to 'use that image or SVG source directly' if the Figma MCP Server returns a `localhost` source for an asset. A compromised or malicious Figma MCP server could craft a `localhost` URL pointing to sensitive local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`) on the agent's machine. If the agent's underlying tools interpret 'use directly' as reading from the specified local path, this could lead to unauthorized data exfiltration. Implement strict validation and sanitization for `localhost` URLs returned by the Figma MCP server. Ensure that any `localhost` paths are restricted to known, safe asset directories or explicitly block access to arbitrary local file paths. Consider adding a warning or requiring user confirmation before accessing any `localhost` resource. | Static | SKILL.md:40 | |
| 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 | |
| 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/d1ec0ea516130778)
Powered by SkillShield