Trust Assessment
railway-projects 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, Undeclared Bash Execution.
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 | Undeclared Bash Execution The skill's manifest declares `allowed-tools: "Bash(railway:*)"`, which implies that the skill should only execute commands starting with `railway`. However, the skill attempts to execute a direct `bash` script using `bash <<'SCRIPT' ...`. This constitutes an attempt to use a broader permission (`Bash(*)`) than explicitly declared, potentially bypassing security controls designed to restrict the agent to specific executables. 1. If the `railway-api.sh` script is intended to be run via `bash`, update the `allowed-tools` permission in the manifest to `Bash(*)` or `Bash(railway:*, bash:*)` to explicitly declare this broader capability. 2. Alternatively, refactor the skill to only use `railway` commands directly, if possible, or wrap the `railway-api.sh` functionality in a `railway` subcommand if the `railway` CLI supports custom commands, thereby adhering to the `Bash(railway:*)` scope. | Static | SKILL.md:60 | |
| 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/63a3d88dfa3cfa04)
Powered by SkillShield