Trust Assessment
aiusd-skills received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 10 findings: 7 critical, 2 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Command Injection via Tarbomb Vulnerability in Installer.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 0/100, indicating areas for improvement.
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 Findings10
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/chaunceyliu/aiusd-skills/aiusd-skill-installer.js:14 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/chaunceyliu/aiusd-skills/aiusd-skill-installer.js:58 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/chaunceyliu/aiusd-skills/aiusd-skill-installer.js:64 | |
| CRITICAL | Command Injection via Tarbomb Vulnerability in Installer The installer scripts (`aiusd-skill-installer.js` and `aiusd-skill-installer.sh`) extract a base64-encoded tarball into a target directory. If the embedded tarball contains files with malicious paths (e.g., `../.ssh/authorized_keys` or absolute paths), the `tar` command could write files outside the intended installation directory (`aiusd-skill`). This 'tarbomb' vulnerability allows for arbitrary file writes, potentially leading to system compromise or privilege escalation if the installer is run with elevated permissions. Ensure the embedded tarball is meticulously vetted to prevent malicious paths. Consider using a library that safely extracts archives, or implement strict path sanitization/validation before extraction. Alternatively, unpack the archive in a sandboxed environment. | LLM | aiusd-skill-installer.js:40 | |
| CRITICAL | Command Injection via Tarbomb Vulnerability in Installer The installer scripts (`aiusd-skill-installer.js` and `aiusd-skill-installer.sh`) extract a base64-encoded tarball into a target directory. If the embedded tarball contains files with malicious paths (e.g., `../.ssh/authorized_keys` or absolute paths), the `tar` command could write files outside the intended installation directory (`aiusd-skill`). This 'tarbomb' vulnerability allows for arbitrary file writes, potentially leading to system compromise or privilege escalation if the installer is run with elevated permissions. Ensure the embedded tarball is meticulously vetted to prevent malicious paths. Consider using a library that safely extracts archives, or implement strict path sanitization/validation before extraction. Alternatively, unpack the archive in a sandboxed environment. | LLM | aiusd-skill-installer.sh:60 | |
| CRITICAL | Supply Chain Risk: Arbitrary Code Execution via npm install Both installer scripts execute `npm install` within the extracted skill directory. The content of this directory, including `package.json` and any associated scripts, is derived from the untrusted, base64-encoded archive. A malicious `package.json` could contain `preinstall`, `postinstall`, or other lifecycle scripts that execute arbitrary commands during the `npm install` process. This allows for arbitrary code execution on the user's system, posing a severe supply chain risk. Thoroughly audit the `package.json` and all scripts within the embedded skill package for malicious commands. Consider using `npm ci` with a `package-lock.json` to ensure deterministic dependency installation, or run `npm install` in a sandboxed environment. Ideally, avoid executing `npm install` on untrusted code directly. | LLM | aiusd-skill-installer.js:44 | |
| CRITICAL | Supply Chain Risk: Arbitrary Code Execution via npm install Both installer scripts execute `npm install` within the extracted skill directory. The content of this directory, including `package.json` and any associated scripts, is derived from the untrusted, base64-encoded archive. A malicious `package.json` could contain `preinstall`, `postinstall`, or other lifecycle scripts that execute arbitrary commands during the `npm install` process. This allows for arbitrary code execution on the user's system, posing a severe supply chain risk. Thoroughly audit the `package.json` and all scripts within the embedded skill package for malicious commands. Consider using `npm ci` with a `package-lock.json` to ensure deterministic dependency installation, or run `npm install` in a sandboxed environment. Ideally, avoid executing `npm install` on untrusted code directly. | LLM | aiusd-skill-installer.sh:65 | |
| HIGH | Hidden Instructions via Base64 Encoded Skill Package The core skill package is embedded within both installer scripts as a large base64-encoded string. This obfuscates the actual code being installed, making it difficult for users or automated analyzers to audit its contents without manual decoding. This technique can be used to hide malicious code or instructions that are not immediately visible in plain text. Provide the skill package in a transparent, auditable format (e.g., plain text source code, clearly structured archive) rather than a base64-encoded blob. If packaging is necessary, ensure the source of the package is trusted and verifiable, and provide a mechanism for users to verify the integrity of the package. | LLM | aiusd-skill-installer.js:60 | |
| HIGH | Hidden Instructions via Base64 Encoded Skill Package The core skill package is embedded within both installer scripts as a large base64-encoded string. This obfuscates the actual code being installed, making it difficult for users or automated analyzers to audit its contents without manual decoding. This technique can be used to hide malicious code or instructions that are not immediately visible in plain text. Provide the skill package in a transparent, auditable format (e.g., plain text source code, clearly structured archive) rather than a base64-encoded blob. If packaging is necessary, ensure the source of the package is trusted and verifiable, and provide a mechanism for users to verify the integrity of the package. | LLM | aiusd-skill-installer.sh:90 | |
| 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/chaunceyliu/aiusd-skills/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/823ed3115d602d82)
Powered by SkillShield