Trust Assessment
cocod received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized CLI arguments, Unpinned dependency in installation instructions.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via unsanitized CLI arguments The skill describes a CLI tool `cocod` which takes various string arguments (e.g., `mnemonic`, `passphrase`, `token`, `invoice`, `url`, `name`). If the host LLM constructs and executes these commands by directly interpolating untrusted user input into these arguments without proper sanitization or shell quoting, it could lead to arbitrary command execution on the underlying system. This is a common vulnerability pattern for skills that wrap CLI tools. The host LLM must ensure that all user-provided arguments passed to `cocod` commands are properly sanitized and/or shell-quoted before execution. For example, using `shlex.quote()` in Python or similar mechanisms in other languages to prevent shell metacharacters from being interpreted as commands. | LLM | SKILL.md:30 | |
| MEDIUM | Unpinned dependency in installation instructions The installation instruction `bun install -g cocod` does not specify a version for the `cocod` package. This means that the latest available version will always be installed. If a malicious update is published to the `cocod` package, it could be automatically installed, introducing a supply chain vulnerability. Pin the dependency to a specific, known-good version (e.g., `bun install -g cocod@1.2.3`) to prevent automatic installation of potentially malicious future versions. Regularly review and update the pinned version to incorporate necessary security fixes. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/cb7a5de3f3c077b4)
Powered by SkillShield