Security audit

Namegarage Catalog — Domain Search

Security checks for vulnerabilities and agentic risk

Overview

The skill provides narrowly scoped public domain searches and price checks, sending search terms to Namegarage.

Use general keywords instead of confidential project details, since search text is sent to Namegarage. Credentials are unnecessary, and purchases remain outside this skill.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The search workflow sends project descriptions or keywords to a third-party service without a privacy warning.

Medium

Category: Output Handling
Confidence: 97% confidence
Finding: The skill instructs the agent to submit project descriptions or keywords to Namegarage through a search query. It does not warn that this transmits user-provided content to an external service, which matters when descriptions contain confidential project or business information.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.