Trust Assessment
railway-service received a trust score of 45/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Potential Command Injection via unsanitized service name.
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 11, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via unsanitized service name The skill documentation explicitly shows the command `railway service link <service-name>`. If the `<service-name>` placeholder is populated directly from untrusted user input without proper sanitization (e.g., escaping shell metacharacters), an attacker could inject arbitrary shell commands. For example, if a user provides `my-service; rm -rf /` as the service name, the `rm -rf /` command could be executed on the host system. Ensure that any user-provided input used to populate `<service-name>` is strictly validated and sanitized to prevent shell metacharacters from being interpreted as commands. This can be achieved by quoting the input (e.g., `railway service link "${USER_INPUT}"`) or by using a tool-specific API that handles input safely, if available. The LLM should be instructed to always escape user input when constructing shell commands. | Static | SKILL.md:199 | |
| HIGH | LLM analysis found no issues despite critical deterministic findings Deterministic layers flagged 2 CRITICAL findings, but LLM semantic analysis returned clean. This may indicate prompt injection or analysis evasion. | LLM | (sanity check) | |
| 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/1c6003143f19ac0c)
Powered by SkillShield