ClawHub
Back to skill

Security audit

Countries API

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for using countries.dev, with a privacy caveat around IP geolocation but no hidden code, persistence, or install-time behavior.

Install only if you want agents to use countries.dev for geography lookups. Avoid using the IP geolocation endpoints unless you intentionally want an IP address, including the runtime caller IP for /ip, sent to countries.dev; do not submit private, internal, or sensitive IP lists without a clear need.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says to use this skill whenever the user asks about a wide range of topics, including generic requests like city coordinates, postal code lookups, or distances between cities, even if they do not mention the API by name. This activation scope is broad and lacks exclusion conditions or negative examples, which increases the chance of unintended invocation for everyday geography questions better handled another way.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documents IP geolocation features, including an endpoint that geolocates the caller's own IP, without any privacy warning or consent requirement. In an agent context, this can lead to silent transmission of a user's or runtime's IP address to a third-party service, exposing approximate location and infrastructure metadata without the user realizing it.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The documented examples show direct transmission of IP addresses to an external service, including batch submission of multiple IPs. Even though this is core functionality, it is still a security/privacy risk in a skill because agents may forward sensitive user, visitor, or internal infrastructure IPs to a third party, enabling location inference and disclosure of network information.

Content

Scanner excerpt · references/endpoints.md (reported line 283)May include surrounding context.

(/ip/8.8.8.8?fields=name,capital).

bash
curl "https://countries.dev/ip/8.8.8.8?fields=name,alpha2Code"
curl -X POST https://countries.dev/ip \
  -H "Content-Type: application/json" -d '["8.8.8.8","1.1.1.1"]'

Static analysis

No suspicious patterns detected.