ClawHub
Back to skill

Security audit

OpenLang

Security checks for vulnerabilities and agentic risk

Overview

This is a compact agent-to-agent communication format with no executable payload, install hook, persistence, or hidden data access, though users should understand that its default compressed form is less readable than normal language.

Install this only if you are comfortable with agents using a compressed notation when talking to other agents. For sensitive workflows, prefer keeping decoded or plain-language logs available so human reviewers can understand what was requested and returned.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill directs agents to use a specialized compressed protocol by default for inter-agent communication without explicit user opt-in. While not directly enabling code execution, this can reduce transparency, hinder human oversight, and make it easier for unsafe or policy-violating instructions to be obscured in agent-to-agent channels.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The rules section mandates default use of OpenLang for all agent-to-agent messages, removing language choice and normalizing an opaque communication layer. In multi-agent systems, enforced compact protocols can impede review, monitoring, and policy enforcement, increasing the chance that harmful instructions or sensitive data transfers go unnoticed.

Static analysis

No suspicious patterns detected.