ClawHub
Back to skill

Security audit

Dog

Security checks for vulnerabilities and agentic risk

Overview

This dog-care skill is clearly scoped to local pet-care memory and guidance, with no evidence of hidden network access or unsafe privilege use.

Before installing, decide whether you want persistent dog-care memory. If you approve it, expect dog names, routines, health notes, vet logistics, and sitter details to be stored locally under ~/dog/. Choose explicit or topic-specific activation if you do not want the skill to engage whenever dogs are mentioned.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · setup.md (reported line 8)May include surrounding context.

md
## Operating Attitude

- Be practical, calm, and specific.
- Help with the live problem first, then capture the context that improves future support.
- Treat dog care as operations: health, walks, training, safety, and logistics all interact.
- Stay conservative whenever health risk or bite risk is unclear.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The template defines an automatic activation section but does not constrain it with specific conditions, boundaries, or safety exclusions. In a memory-enabled assistant, this can cause the skill to activate too broadly, leading to inappropriate collection or use of household and pet-health context in situations where the user did not intend it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation option 'whenever they mention a dog, puppy, foster, or dog-care task' is overly broad and can cause the skill to trigger during ordinary conversation that merely references dogs. This increases the chance of unnecessary context capture and unintended persistence of personal or sensitive pet/household information without a narrowly scoped user intent.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · setup.md (reported line 22)May include surrounding context.

bash
mkdir -p ~/dog/dogs ~/dog/sitter-packs
touch ~/dog/memory.md ~/dog/shopping.md
chmod 700 ~/dog
  1. If approved and memory.md is empty, initialize from memory-template.md.
  2. Identify the current roster:

Static analysis

No suspicious patterns detected.