ClawHub
Back to skill

Security audit

tld-expert

Security checks for vulnerabilities and agentic risk

Overview

This skill uses a clearly disclosed external service for domain suggestions, availability checks, and price comparisons, with no harmful behavior found.

Use non-confidential naming descriptions because queries go to tld.expert. Its data-retention practices and live backend behavior were not established by this artifact review. Confirm final prices and renewal terms with the registrar before purchasing.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The workflow sends user-provided naming briefs to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The workflow directs the agent to send a user's naming brief to tld.expert without first warning that its contents will leave the conversation. Although external domain checks are expected for this skill, full briefs can contain confidential product plans or business details unnecessary for availability checks, and GET query parameters may be retained in service or intermediary logs.

Content

No source excerpt is available for this finding.

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 · references/renewal-traps.md (reported line 54)May include surrounding context.

md
- Dynadot: https://www.dynadot.com/domain/price-list (read 2026-11-05)
- gandi: https://www.gandi.net/en-US/domain/tld (read 2026-11-05)
- Name.com: https://www.name.com/pricing (read 2026-11-05)
- Porkbun: https://api.porkbun.com/api/json/v3/pricing/get (read 2026-11-05)