ClawHub
Back to skill

Security audit

IPinfo

Security checks for vulnerabilities and agentic risk

Overview

This IPinfo connector is mostly coherent, but it should be reviewed because it can trigger sensitive IP lookups directly and includes unverified remote installer commands.

Review before installing. Use it only when you explicitly want an IPinfo/OOMOL lookup or write, be careful with current-IP and third-party IP lookups, confirm any bulk upload payload, and prefer a verified installation method for the `oo` CLI rather than directly running remote installer scripts.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill recommends installing the CLI with a 'curl | bash' pattern, which executes a remote script directly without verification. If the distribution endpoint, TLS path, or hosting account is compromised, users may run arbitrary attacker-controlled code on their machine.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The directive 'Use this skill for ANY IPinfo request' is overly broad and can cause the agent to invoke the skill whenever IPinfo is merely mentioned, even when the user's intent is informational, comparative, or does not require connector access. That increases the chance of unnecessary external calls and inadvertent disclosure of user-supplied IPs or metadata to the connected service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill exposes actions that retrieve current IP, geolocation, abuse, privacy, carrier, company, and related enrichment data, but it does not warn that these can reveal sensitive personal or organizational information. In an agent setting, omission of privacy guidance makes it more likely the tool will be used on user, third-party, or current-session IP data without meaningful consent or minimization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.