Security Audit
install-from-remote-library
github.com/skillcreatorai/Ai-Agent-SkillsTrust Assessment
install-from-remote-library received a trust score of 85/100, 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 Shell Command Injection via Untrusted Repository Input.
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 July 1, 2026 (commit 039ad59e). 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 | Shell Command Injection via Untrusted Repository Input The workflow instructions direct the agent to execute shell commands using the `<owner>/<repo>` placeholder directly. If the repository source is supplied by an untrusted user or external source, an attacker can inject shell metacharacters (e.g., `;`, `&&`, `|`) to execute arbitrary commands on the host system. Add explicit instructions in the decision rules or workflow to validate the `<owner>/<repo>` input against a strict regular expression (e.g., matching only alphanumeric characters, hyphens, and a single slash: `^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$`) before executing any shell commands. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/6dc984a387a3a380)
Powered by SkillShield