ClawHub
Back to skill

Security audit

Firm Platform Audit Pack

Security checks for vulnerabilities and agentic risk

Overview

This is a small audit-instruction skill with no bundled code or persistence, and its sensitive checks are disclosed and tied to user-provided OpenClaw configuration files.

Before installing, confirm you have or trust the declared mcp-openclaw-extensions dependency, because this skill appears to document calls to external OpenClaw audit tools rather than bundle their implementations. Run the checks only on configuration files you intend to audit.

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
89% confidence
Finding
The only user-facing warning in the document is written in French: "Contenu généré par IA — validation humaine requise avant utilisation." This creates a language/locale policy concern because the skill does not offer an opt-in language choice or explain why French is required for this audience.

Static analysis

No suspicious patterns detected.