ClawHub
Back to skill

Security audit

Firm Fleet Manager Pack

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent, but it advertises fleet-wide add, remove, broadcast, and configuration sync actions without enough safety scoping or user-control guidance.

Review this carefully before installing in a real Gateway fleet. Only use it where fleet-wide add/remove, broadcast, and configuration sync operations are intended, and ensure your runtime tooling requires explicit targeting, confirmation, authorization checks, validation, and rollback procedures.

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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises fleet-wide broadcast, add/remove, and configuration synchronization capabilities without clearly warning that these actions can affect multiple Gateway instances simultaneously or cause service disruption. In an orchestration context, under-documented mass-action operations increase the chance of accidental misuse, broad configuration drift, or outage-causing commands being applied across the entire fleet.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The warning banner is written in French while the rest of the document is in English, and the skill does not indicate that French is required or provide a user language option. This can violate language/locale policy when a specific language is imposed without opt-in or documented regional scope.

Static analysis

No suspicious patterns detected.