Security audit

Deep Research Suite

Security checks for vulnerabilities and agentic risk

Overview

This research skill is a simple Markdown workflow that searches public sources, summarizes findings, and saves reports in a disclosed local folder.

Before installing, be aware that research outputs may be written to memory/research/ and may persist until deleted. Avoid including private or sensitive prompts unless you are comfortable with those summaries being stored locally.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly states that generated research reports are saved to memory/research/, but it does not clearly warn the user up front that running the skill will write files to persistent storage. Automatic writes can create privacy, data retention, or workspace clutter issues, especially if prompts or synthesized content contain sensitive information.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.