Back to skill

Security audit

Uws Publish

Security checks across malware telemetry and agentic risk

Overview

This is a coherent web-search skill that sends search queries to configured third-party search providers, with privacy caveats users should understand.

Install only if you are comfortable with your search queries, domains, date filters, and related parameters being sent to whichever configured provider the skill routes to or falls back to. Configure only the providers you intend to use, and do not search for credentials, private customer data, regulated content, or confidential internal material unless your organization permits that provider handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill advertises use of environment variables and references implementation files that imply network, file read, and possibly file write capabilities, but it does not declare permissions or otherwise warn operators about those capabilities. This creates a transparency and governance gap: users or platforms may authorize and run the skill without understanding it can access secrets and make external requests.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README advertises unified web search across multiple third-party providers but does not clearly warn that user queries will be transmitted to external vendors. In an agent-skill context, users may assume a local capability; silent forwarding can expose sensitive prompts, internal URLs, or proprietary data to outside services and create compliance/privacy issues.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documented automatic key rotation, failover, and multi-provider routing mean a single query may be retried with alternate vendors, yet the README does not disclose that behavior to users. This increases the privacy and governance risk because a failed request may still result in broader-than-expected dissemination of the same query across multiple external services.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill sends user search queries to multiple third-party providers, but the documentation does not clearly warn that query content may leave the local environment and be processed by external services. Users may unknowingly submit sensitive, regulated, or proprietary information, leading to privacy, compliance, or data handling risks.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The search() path sends user queries, site filters, date ranges, and related search context to multiple third-party providers based on routing logic, but this file contains no consent gate, disclosure, or redaction layer. In a skill context, users may reasonably assume a local tool, so sensitive prompts or internal keywords could be unintentionally transmitted outside the trust boundary.

External Transmission

Medium
Category
Data Exfiltration
Content
end_date: Optional[date] = None,
    topic: str = "general",
) -> dict:
    endpoint = "https://api.tavily.com/search"
    payload = {
        "api_key": api_key,
        "query": query,
Confidence
92% confidence
Finding
https://api.tavily.com/

External Transmission

Medium
Category
Data Exfiltration
Content
def _tencent_wsa_search_with_key(api_key: str, query: str) -> dict:
    endpoint = "https://api.wsa.cloud.tencent.com/SearchPro"
    payload = {"Query": query}
    try:
        data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
Confidence
90% confidence
Finding
https://api.wsa.cloud.tencent.com/

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.