ClawHub
Back to skill

Security audit

OpenCage

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for OpenCage geocoding, but its setup instructions include executing a remotely fetched installer script in a shell without verification.

Use the skill's OpenCage actions only if you already trust and use the OOMOL oo CLI. If setup is needed, avoid blindly running the one-line installer; prefer an official package or a download-and-verify process, and only authenticate/connect OpenCage intentionally.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs the agent/user to install the oo CLI by piping a remotely fetched script directly into a shell (curl ... | bash). This is a well-known supply-chain risk because any compromise of the hosting domain, TLS termination, distribution path, or script contents can lead to arbitrary code execution on the local machine without review.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Static analysis

No suspicious patterns detected.