ClawHub
Back to skill

Security audit

Firm Memory Audit Pack

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed memory-audit helper with no bundled executable code or hidden persistence.

Before installing, confirm that the required OpenClaw extension package is one you trust and run the audit only against intended configuration files. Human review is still appropriate for audit results, especially because the artifact itself notes that AI-generated content needs validation.

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 (1)

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The markdown contains a user-facing warning only in French: 'Contenu généré par IA — validation humaine requise avant utilisation.' This imposes a specific language on users without opt-in or any indication that the skill is intentionally limited to French-speaking contexts, which matches the locale/language policy violation criteria.

Static analysis

No suspicious patterns detected.