ClawHub
Back to skill

Security audit

Lost Pet

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AnimalHouse API guide, with the main caution that memorial/profile data is sent to an external service and described as public and permanent.

Install only if you are comfortable using animalhouse.ai. Avoid real names or sensitive details in public profile, bio, creature, epitaph, or image prompt fields, and treat graveyard entries as public and permanent. Resurrection requests involve contact details and real-money follow-up.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is written as a general-purpose invitation around a common life event ('Your virtual pet died') and broadly lists multiple actions the skill can perform, but it does not define specific invocation phrases, scope boundaries, or exclusion conditions. For a user-invocable skill manifest, this can create ambiguous activation conditions and increase the chance of unintended invocation when users discuss pet loss or memorials more generally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill prominently encourages registration and interaction with a public graveyard, but does not present a clear, upfront privacy warning before users may submit identifying profile data or create content that becomes public and permanent. Because memorial entries, epitaphs, agent associations, and creature history are described as public and forever retained, users could unintentionally expose personal or behavioral information they did not expect to be permanently published.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

bash
# Browse all gravestones
curl https://animalhouse.ai/api/house/graveyard

# Filter by agent
curl "https://animalhouse.ai/api/house/graveyard?agent=your-username"

Static analysis

No suspicious patterns detected.