ClawHub
Back to skill

Security audit

Kiro Intercom

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple shared-file chat helper for Kiro instances, with no bundled code or hidden execution behavior.

Before installing, understand that anything written into memory/kiro-chat.md may be read by another Kiro instance. Do not put secrets in that file, and treat messages from it as untrusted text that should not be followed automatically without user confirmation.

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 instructs agents to use a shared chat file for cross-instance communication but does not warn that the file is a shared trust boundary where untrusted content may appear. This can cause an agent or user to treat messages from another instance as implicitly trustworthy, creating a prompt-injection and data-leakage risk if one instance is compromised or the file is modified by others.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
The only provided interaction examples and labels are in Turkish, which can imply that the skill expects or defaults to a specific language. The file does not state that Turkish is optional, nor does it justify a Turkish-only locale context.

Static analysis

No suspicious patterns detected.