Trust Assessment
railway-templates received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 1 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Broad Bash execution permissions for `railway` CLI.
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 | |
|---|---|---|---|---|
| HIGH | Broad Bash execution permissions for `railway` CLI The skill declares `Bash(railway:*)` in its manifest, granting it the ability to execute any command starting with `railway`. While the `SKILL.md` only shows examples of `railway status` and calls to a helper script (`railway-api.sh`), this broad permission allows the skill to potentially perform destructive or unintended operations (e.g., `railway delete`, `railway env set`, `railway link`) if a malicious user can manipulate the skill's input to construct such commands. This is a common risk when wrapping CLIs with overly broad permissions. Restrict `Bash` permissions to only the specific `railway` subcommands and arguments absolutely necessary for the skill's intended functionality. For example, if only `railway status` and the custom `railway-api.sh` script are needed, the permissions should be narrowed to reflect that. If `railway-api.sh` is a wrapper for other `railway` commands, then the permissions should be for the specific `railway` commands it calls. | LLM | Manifest | |
| 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 | Unpinned `railway-cli` dependency The skill's manifest declares `railway-cli` as a dependency without specifying a version. This means that the skill could resolve to any version of `railway-cli`, including future versions that might introduce breaking changes, unexpected behavior, or even security vulnerabilities. This lack of pinning makes the skill susceptible to supply chain risks from unverified or malicious updates. Pin the `railway-cli` dependency to a specific, known-good version (e.g., `"railway-cli@2.1.0"`) to ensure consistent behavior and mitigate risks from unexpected or malicious updates. | LLM | Manifest | |
| 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/014530077321375f)
Powered by SkillShield