Trust Assessment
lygo-mint-operator-suite received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized arguments to shell scripts.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via unsanitized arguments to shell scripts The skill's `SKILL.md` describes several Python scripts (`mint_pack_v2.py`, `verify_pack_v2.py`, `bundle_pack_v2.py`, `make_anchor_snippet_v2.py`, `backfill_anchors.py`) that are intended to be executed as shell commands. These commands accept multiple arguments (e.g., `--input`, `--title`, `--version`, `--pack-sha256`, `--out`, `--channel`, `--id`) which are likely to be derived from user input. If an AI agent constructs these shell commands by directly concatenating user-provided values without proper sanitization or escaping, a malicious user could inject arbitrary shell commands. For example, injecting shell metacharacters (such as `;`, `&&`, `|`, `` ` ``) into an argument like `--title` could lead to arbitrary code execution on the host system. When an AI agent constructs shell commands from user input, it must ensure all arguments are properly sanitized and escaped to prevent shell metacharacter injection. It is recommended to use a library function designed for safe command execution (e.g., Python's `subprocess.run` with `shell=False` and passing arguments as a list) rather than concatenating strings directly. The AI agent should also implement robust validation and sanitization of user input before passing it to these scripts. | LLM | SKILL.md:23 |
Scan History
Embed Code
[](https://skillshield.io/report/6157814784deb9c8)
Powered by SkillShield