Seo Keyword Research

• Outcome: Review
• Latest audit: May 27, 2026, 9:34 PM
• Version:
  1.0.0

Overview

The skill appears to be an SEO research helper, but its routing text is broader than that purpose and could invoke a third-party, API-key-backed service for generic web research or content extraction.

Install only if you intend to use AIsa for SEO keyword research and are comfortable sending supplied domains, crawled page content, keyword data, competitor names, and prompts to api.aisa.one. Avoid using it as a general web research or content extraction tool, confirm country and language before running queries, and treat generated output files as potentially sensitive business strategy.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The manifest declares required binaries, environment variables, and network targets, but the finding indicates the skill's effective capabilities also include file read/write without an explicit permission model. That mismatch can lead reviewers or execution frameworks to underestimate what the skill can access, especially since it handles an API key and may process website content, increasing the risk of unintended data access or exfiltration.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The plugin description advertises broad use cases such as 'web search, research, source discovery, or content extraction,' which extend well beyond SEO keyword research. In agent ecosystems that rely on natural-language descriptions for tool selection, this can cause the plugin to be invoked for unrelated browsing or extraction tasks, unnecessarily exposing external network access and the supplied API key to requests outside its intended scope.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The description contains broad activation triggers such as requests for web search, research, source discovery, content extraction, and many SEO-related tasks. Overly general routing language can cause the skill to activate outside its narrow intended use, exposing the AISA API key, enabling unnecessary crawling/network activity, or handling content that should have been processed by a less-privileged tool.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The manifest description uses very broad trigger language such as 'web search, research, source discovery, or content extraction,' which extends well beyond narrowly scoped SEO keyword research. In an agent environment, this can cause the plugin to be selected for generic browsing and extraction tasks, unnecessarily granting a third-party networked skill access to user prompts, provided URLs, and derived content.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The command description repeats the same ambiguous routing criteria, increasing the chance that the command is auto-invoked for loosely related requests rather than only for SEO keyword analysis. Because the skill requires an API key and sends requests to an external service, overbroad invocation expands unnecessary data exposure and external dependency use.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The package description is broad enough to route generic web search, research, source discovery, and content extraction requests into this skill, even though it is framed as an SEO keyword research plugin. That increases the chance the agent invokes a networked third-party plugin with an API key for tasks outside the user's intended scope, causing unnecessary data exposure and over-privileged tool use.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The README tells the agent to use this skill not only for SEO keyword research tasks, but also whenever the user needs general web search, research, source discovery, or content extraction. That scope is substantially broader than the stated skill purpose and can cause the agent to invoke an external API-powered plugin in situations outside its intended domain, increasing the chance of unnecessary data exposure, over-collection, and misuse of third-party capabilities.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The skill description explicitly expands its use beyond SEO keyword research to broad web search, research, source discovery, and content extraction. That scope creep can cause over-invocation for general browsing or data gathering tasks, increasing unnecessary crawling and third-party data transmission outside the user's likely intent.

Natural-Language Policy Violations

Medium

• Confidence: 74% confidence
• Finding: Defaulting to United States and English without explicit user confirmation can lead to silent use of the wrong market, causing unintended third-party queries and inaccurate outputs. This is primarily a consent and data-quality issue rather than a direct compromise, but it can affect privacy expectations and decision-making.

VirusTotal

62/62 vendors flagged this plugin as clean.