Trust Assessment
json-canvas 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 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Potential for sensitive file path disclosure via 'file' node type.
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 | Potential for sensitive file path disclosure via 'file' node type The skill defines a 'file' node type with a 'file' attribute, explicitly described as 'Path to file within the system'. A malicious prompt could instruct the LLM to generate JSON Canvas files containing paths to sensitive system files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, `C:\Windows\System32\config\SAM`). While the skill itself does not perform file system access or exfiltration, it provides a structured output format that can be used by the LLM to enumerate or reference sensitive file locations. If this output is subsequently processed by an application with file system access, it could lead to unintended data disclosure or reconnaissance. Implement strict validation and sanitization of file paths generated for 'file' nodes. Restrict paths to a safe, sandboxed directory (e.g., project-specific directories) or disallow absolute/system paths. The LLM should be explicitly instructed to avoid generating paths to sensitive system files or directories, especially when handling untrusted user input or when the context does not explicitly require such access. | LLM | SKILL.md:101 | |
| 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/40c988322ca82310)
Powered by SkillShield