Back to skill

Security audit

jike-seo

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SEO keyword lookup skill, but users should know it sends search terms to a third-party API and its check command prints part of the API key.

Install only if you trust the dso100/Jike SEO service with your keyword queries and API-backed access. Avoid searching confidential client names, campaign plans, or unreleased product terms, and avoid running the check command in shared terminals or logs because it shows part of the configured API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Low
Confidence
95% confidence
Finding
The check command claims to validate API connectivity, but it only checks whether the API key exists locally and then prints part of it. This can mislead users into believing the remote service is reachable and authenticated when no network validation has occurred.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation text is very broad and can trigger on common SEO, keyword, content, trend, and competitor-analysis discussions without clear boundaries. Overbroad invocation can cause unintended external queries and disclosure of user-supplied business terms or research interests to the third-party service, even when the user did not explicitly consent to using this tool.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Although the file mentions API-key authentication internally, it does not clearly warn end users that their keyword queries will be transmitted to an external service authenticated with a stored secret. This is dangerous because keyword research terms may reveal confidential campaign plans, client names, products, or market strategy, and users are not given meaningful notice before data leaves the local environment.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The check command reveals the first and last characters of the API key to stdout. Partial secret disclosure can aid credential correlation, leak into logs or transcripts, and increase exposure in shared terminal or agent environments.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.