ClawHub
Back to skill

Security audit

Dns Agent Skills

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent DomainHelp DNS utility skill catalog that sends requested DNS, domain, URL, and network-identity checks to documented external API endpoints.

Install only if you are comfortable sending queried domains, URLs, and network metadata to DomainHelp. Avoid submitting secrets, internal-only hostnames, private links, or URLs with tokens unless that exposure is acceptable for your environment.

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
  • 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 (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The catalog explicitly directs agents to remote execution endpoints and lists skills that accept domains, URLs, and request-derived data, but it provides no privacy warning about transmitting potentially sensitive user input or requester metadata to a third-party service. In agent contexts, users may assume local analysis unless disclosure is made, so this omission can lead to unintentional exposure of internal URLs, domains under investigation, or client IP/resolver information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README documents skills that intentionally reveal requester network metadata such as public IP address and recursive DNS resolver, but it provides no privacy warning or consent guidance. In an agent setting, users may invoke these tools without realizing their IP, resolver, and related network attributes will be disclosed to an external service, creating avoidable privacy and operational security risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The README advertises URL/domain analysis and expansion endpoints without warning that submitted domains and URLs are sent to a third-party external service. In agent workflows, this can leak sensitive internal hostnames, private links, investigation targets, or user browsing artifacts, especially for redirect-chain and related lookup functions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The catalog advertises multiple skills that send user-supplied domains, URLs, resolver checks, and related request metadata to external DomainHelp endpoints, but it does not clearly warn users that these inputs and associated client metadata will be transmitted to a third-party service. In an agent setting, users may assume analysis is local; this creates a privacy and data-handling risk, especially for sensitive internal domains, investigation targets, or URLs containing tokens or confidential parameters.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The prompt starter for the redirectchain skill encourages use of a tool that makes outbound HTTP requests and captures response data, but it does not warn users or downstream agents that invoking it will contact third-party URLs and may collect sensitive metadata. This can lead to unintended SSRF-like behavior, privacy leakage, or unsafe handling of attacker-controlled URLs in automated workflows, especially when an agent follows user-supplied links without explicit confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill directs agents to call a third-party endpoint that necessarily reveals the caller's public IP address and associated request metadata to DomainHelp, but the documentation does not clearly warn about that disclosure. This can create unintended privacy leakage, especially when invoked from sensitive environments such as corporate networks, developer machines, or hosted agents where the egress IP and timing metadata may be operationally sensitive.

Content

No source excerpt is available for this finding.