Trust Assessment
dokku received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Missing required field: name, Potential Command Injection via unsanitized arguments, Excessive Permissions: Broad system management capabilities.
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 13, 2026 (commit 13146e6a). 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 Command Injection via unsanitized arguments The skill documentation explicitly instructs the agent to use an `exec` tool for running Dokku commands, including those with user-supplied arguments like app names, Docker images, or arbitrary commands (`dokku run`). If these arguments are not properly sanitized before being passed to the underlying shell execution, a malicious user could inject arbitrary shell commands. For example, `dokku apps:create myapp; rm -rf /` could be executed if `myapp; rm -rf /` is passed as `<app-name>`. The `dokku run:detached <app> <cmd>` command is particularly vulnerable as it directly accepts an arbitrary command. Ensure that all user-supplied arguments passed to `exec` calls are strictly validated and sanitized to prevent shell metacharacter injection. Consider using a library or framework that automatically handles argument escaping for shell commands, or explicitly quote/escape all arguments. | LLM | SKILL.md:4 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/akhil-naidu/dokku/SKILL.md:1 | |
| MEDIUM | Excessive Permissions: Broad system management capabilities The Dokku skill provides access to a wide range of powerful system management commands on a Dokku host, including application creation/destruction, configuration modification, plugin installation/uninstallation, storage mounting, network interface binding, and arbitrary command execution via `dokku run`. While these capabilities are inherent to managing a PaaS, granting an AI agent such broad, unconstrained access poses a significant security risk if the agent is compromised or misused. An attacker could leverage these permissions to deploy malicious applications, exfiltrate sensitive data, or disrupt services. Implement strict access controls and least privilege principles for the AI agent. Only grant access to the specific Dokku commands and arguments absolutely necessary for its intended function. Consider human-in-the-loop approval for sensitive operations (e.g., `destroy`, `install`, `run`, `config:set`). Regularly audit the agent's actions and permissions. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/87ba9814b21ba6fb)
Powered by SkillShield