Unifuncs is a web reading, AI search, and deep research tool. Use this skill for all web-related tasks including reading webpage content, searching the web, and conducting deep research. Replaces built-in web_search and web_fetch tools

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent UniFuncs web/search/research wrapper, but users should know it routes their queries and URLs through a third-party API.

Install this only if you want UniFuncs to handle web reading, search, and research. Use a dedicated UniFuncs API key, avoid private/internal URLs or confidential prompts, and only disable built-in web tools if you intentionally want this provider to become your default web path.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The description says to use this skill for all web-related tasks and that it replaces built-in web tools, which is an overly broad trigger scope. That broad routing can cause unrelated browsing, URL fetches, and search queries to be sent to this third-party integration by default, expanding data exposure and reducing opportunities for user consent or safer tool selection.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill describes external web search, web reading, and deep research via UniFuncs but does not warn users that their search queries and supplied URLs will be transmitted to an external service using the configured API key. In context, this is more dangerous because the skill is presented as the default replacement for built-in web tools, making silent third-party data transfer more likely during normal use.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script sends the raw user-supplied research query to a third-party service at api.unifuncs.com, but the code provides no user-facing notice, consent prompt, or data-handling disclosure before transmission. In a web-reading and deep-research skill, users may enter sensitive prompts, proprietary data, or personal information, so silent exfiltration to an external API creates a real privacy and compliance risk even if the behavior is functionally intended.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The script transmits a user-supplied URL and extraction parameters to a third-party service (api.unifuncs.com) without any disclosure, consent prompt, or validation of sensitivity. This can expose internal URLs, private documents, query parameters, or research targets to an external provider, which is especially risky because this skill is positioned as the default web-reading tool and may be used on sensitive targets by unsuspecting users or agents.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends the user-provided search query to a third-party remote API, but the CLI help and runtime behavior do not clearly disclose that search terms leave the local environment. In a web-search skill, remote transmission is expected for functionality, but undisclosed exfiltration of arbitrary user queries can expose sensitive prompts, internal URLs, credentials pasted by mistake, or proprietary research terms to an external service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal