ClawHub
Back to skill

Security audit

Chat

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently stores communication preferences locally so the agent can adapt its response style.

Install this only if you want the agent to remember communication-style preferences across sessions in local files under ~/chat. Avoid storing sensitive personal details there, and use the documented forget/show controls to review or remove entries.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 6)May include surrounding context.

md
slug: chat
version: 1.1.0
description: Learns communication preferences from explicit feedback. Adapts tone, format, and style.
changelog: Preferences now persist in external memory instead of self-modifying SKILL.md
metadata: {"clawdbot":{"emoji":"💬","requires":{"bins":[]},"os":["linux","darwin","win32"]}}
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly persists user communication preferences in local files under ~/chat, but the description and rules do not require clear advance notice or opt-in for retention. Even if the data is framed as non-sensitive, preferences can still reveal behavioral traits or private context, and silent persistence creates a privacy risk if users are unaware their data is being stored across sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.