Security Audit
browse-and-evaluate
github.com/skillcreatorai/Ai-Agent-SkillsTrust Assessment
browse-and-evaluate received a trust score of 78/100, 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 untrusted input in CLI arguments, Supply Chain Risk: Unpinned `npx` package version for `ai-agent-skills`.
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 June 1, 2026 (commit 039ad59e). 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 untrusted input in CLI arguments The skill constructs shell commands using user-provided input for placeholders like `<query>` and `<skill-name>` (e.g., `npx ai-agent-skills search <query>`). If the `ai-agent-skills` CLI tool does not adequately sanitize or escape these arguments before internal processing or execution, an attacker could inject shell metacharacters (e.g., `;`, `&&`, `|`, `$()`) to execute arbitrary commands on the host system. This pattern is a common source of command injection vulnerabilities in agent skills that interact with external CLI tools. Ensure that all user-provided inputs (`<query>`, `<skill-name>`) are strictly validated and/or properly escaped before being passed to shell commands. The `ai-agent-skills` CLI should be hardened against command injection. The skill itself could add a guardrail to sanitize inputs before passing them to the CLI, or explicitly state that inputs must be sanitized. | Static | SKILL.md:20 | |
| MEDIUM | Supply Chain Risk: Unpinned `npx` package version for `ai-agent-skills` The skill uses `npx ai-agent-skills` without specifying a version (e.g., `ai-agent-skills@latest` or `ai-agent-skills@4.1.0`). This means `npx` will always fetch and execute the `latest` version available on the npm registry. This introduces a supply chain risk, as a compromised `latest` version of the `ai-agent-skills` package could lead to arbitrary code execution on the agent's host system. A malicious actor gaining control of the package or a typosquatting attack could exploit this. Pin the version of the `ai-agent-skills` package used by `npx` to a specific, known-good version (e.g., `npx ai-agent-skills@4.1.0`). Regularly review and update the pinned version to benefit from security patches while maintaining control over the deployed version. | Static | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/a581be8e6542d0eb)
Powered by SkillShield