Back to skill

Security audit

123

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tavily web search helper that sends user-provided searches or URLs to Tavily using the user's Tavily API key.

Install this only if you are comfortable sending search queries, requested URLs, and your Tavily API key to Tavily's API. Avoid using it for confidential prompts, private internal URLs, or sensitive data unless Tavily is an approved provider for that information.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes Node scripts that require environment access (TAVILY_API_KEY) and perform outbound network requests to Tavily, but the manifest does not explicitly declare a tool scope such as permissions or allowed-tools. This creates an authorization gap where the runtime capabilities are broader or less transparent than what the skill contract communicates, increasing the risk of unintended secret access or network use.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/extract.mjs (reported line 24)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/extract.mjs (reported line 24)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/search.mjs (reported line 62)May include surrounding context.

js
process.exit(1);
}

const resp = await fetch("https://api.tavily.com/extract", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The script sends both the user-supplied search query and the Tavily API key to an external service, but provides no runtime notice, consent prompt, or data-handling warning. This can expose sensitive prompts or operational secrets if users assume the tool performs only local processing or are unaware that arbitrary query text is transmitted off-host.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/search.mjs (reported line 62)May include surrounding context.

js
body.days = days;
}

const resp = await fetch("https://api.tavily.com/search", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest describes an AI-optimized web search skill, but the code also accesses process environment state to obtain credentials. While this may be operationally necessary, credential access is a separate capability not reflected in the stated purpose and is specifically the kind of capability that can be unjustified when omitted from the manifest description.

Content

No source excerpt is available for this finding.