Analyze an AI skill URL for prompt injection, malware, and OWASP LLM Top 10 threats to verify safety before installation.
Analyze an AI agent skill for prompt injection, malware patterns, and OWASP LLM Top 10 issues BEFORE installing it (SecurityScan).
| Name | Required | Description | Default |
|---|---|---|---|
| skill_url | Yes | URL of the skill to analyze (e.g. a GitHub skill URL). |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the responsibility of conveying behavior. It indicates that this is an analysis/scan rather than an installation, and names the categories checked, but it does not explicitly state whether the tool downloads the skill, executes it, or only inspects it, nor what limitations apply.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one tight sentence that front-loads the action and key security concerns. Every element contributes: the subject, the danger categories, and the timing advisory. There is no filler or redundant phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has only one well-documented parameter and an output schema, so the description does not need to explain return values. It covers the essential context, including the security concerns and the pre-install timing, though a brief note on non-execution or side-effect-free behavior would make it fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter skill_url is already fully documented in the input schema with an example, giving 100% schema description coverage. The description repeats the concept of analyzing a skill but adds no material semantic detail beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb (Analyze), a clear resource (AI agent skill), and concrete objectives (prompt injection, malware patterns, OWASP LLM Top 10). It also adds the important context of running it before installation, which clearly distinguishes it from sibling scanning tools like network_scan, scan_secrets, or audit_mcp_server_config.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'BEFORE installing it' gives a clear when-to-use signal, and the threat categories make it evident this is a skill-safety pre-flight check. It implicitly differentiates itself from sibling tools that target other artifact types, but it does not explicitly list exclusions or when to prefer a sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.