Security audit

Exa Researcher

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Exa research helper, but it gives broad people-search, web-crawling, deep-research, and memory-use guidance without enough scope or privacy controls.

Install only if you are comfortable with the agent using Exa for broad web research, including people and company lookups, crawling, long-running research tasks, and possibly saving findings to memory. Use it with explicit instructions about scope, privacy, and what not to store.

A.I.G

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

SkillSpector

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description uses very broad trigger phrases such as 'conduct web research', 'gather company information', and 'any knowledge-intensive research needs', which can cause the agent to invoke this skill for a wide range of ordinary requests. In a skill that enables people search, company profiling, crawling, and deep research, over-broad activation increases the chance of unnecessary data collection or privacy-sensitive tool use without clear user intent.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill documents people research and web crawling capabilities without user-facing warnings or guardrails around privacy, consent, scope, or acceptable use. In this context, the omission is risky because these tools can be used to compile personal profiles or crawl sites in ways users may not expect, increasing privacy, compliance, and misuse risk.