Security audit

Preflighting Domains

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only domain pre-flight helper whose DNS and connection-checking behavior matches its stated purpose.

Install this if you want agents to inspect DNS/provider readiness for customer domains. Be aware it depends on the doDomain connector and OAuth, and it may read existing team connection records for the domain being checked, but the skill instructs the agent not to create, verify, or reverify connections.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description includes the trigger example 'check this domain', which overlaps with common conversational phrasing and does not narrowly constrain when this skill should activate. Although other examples are domain-specific, this phrase is ambiguous enough to match requests outside the intended pre-flight DNS workflow.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.