Security audit

Web Search by Exa

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Exa web-search MCP integration, but its setup encourages API keys in URLs and its people-search examples lack privacy guardrails.

Review before installing. Use the unauthenticated MCP URL where possible, avoid storing an Exa API key directly in a shared URL or config, rotate any key that has been exposed in logs or screenshots, and use people/profile search only for legitimate, authorized public research with appropriate privacy and platform-term checks.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:36
Finding: API Credential Exposed in MCP Endpoint Query Parameters
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill instructs users to place the Exa API key directly in the MCP server URL query string. Secrets embedded in URLs are commonly exposed through config files, logs, process listings, browser/history artifacts, telemetry, screenshots, and shared error reports, creating an avoidable credential leakage risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly promotes people/profile search and LinkedIn-style discovery, and also encourages extracting content from known URLs, including profile URLs, without any privacy, consent, or acceptable-use guidance. In an agent context this increases the chance of collecting, aggregating, or enriching personal data in ways that may violate privacy expectations, platform terms, or internal policy.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.