Skywork Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Skywork web-search skill with normal API-key and privacy cautions, not evidence of hidden or malicious behavior.

Install this only if you intend to use Skywork as an external web-search provider. Do not include secrets, confidential business data, or sensitive personal information in search queries unless you are comfortable sending that text to Skywork. Store SKYWORK_API_KEY carefully, avoid printing it in shared terminals or screenshots, and delete temporary result files after sensitive searches.

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 (3)

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger language is very broad and can cause the skill to activate for many generic research or lookup-style requests, even when live web access is unnecessary. This increases the chance of unnecessary external data access, leakage of user prompts to a third-party search provider, and overuse of a network-enabled skill in contexts where a local answer would suffice.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guide tells users to run `echo "$SKYWORK_API_KEY"`, which prints the full secret to the terminal and potentially into terminal scrollback, screen recordings, logs, shared shells, or support screenshots. Although intended as a simple verification step, instructing plaintext secret display without any warning or safer alternative increases the chance of credential disclosure.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends raw user-provided search queries to a third-party Skywork API without any explicit runtime notice, consent flow, or sensitivity check. Because search queries can contain personal, confidential, or regulated information, this creates a real privacy and data-governance risk, especially in an agent context where users may not realize their input is being transmitted off-box.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal