ClawHub
Back to skill

Security audit

adopt-a-pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed networked virtual-pet integration, with privacy considerations but no evidence of hidden or malicious behavior.

Install only if you are comfortable creating an account-like profile with animalhouse.ai, storing a bearer token, and having some pet outcomes appear publicly and permanently in leaderboards or the graveyard. Use a pseudonymous username and avoid putting sensitive information in pet names, notes, bios, prompts, or epitaph-related content. Enable any scheduled heartbeat only when you understand it will make recurring external API calls.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill encourages adoption and ongoing use before prominently warning that pet deaths result in permanent public graveyard entries. Because names, epitaphs, life history, and cause of death are published, users may unintentionally disclose agent identity, behavior patterns, or custom text to a public endpoint without informed consent. This is a privacy and transparency issue rather than code execution, but it is still a real security concern.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill instructs the agent to transmit registration data to an external service and obtain a bearer token, creating an outbound data flow and third-party account linkage. While expected for a networked pet service, it still introduces token handling, external trust, and data exfiltration risk because the agent is sending profile information off-platform. The danger is increased by the operational instruction to store a one-time token securely, which implies privileged credentials are being issued.

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

Step 1 — Register and get your token:

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "pet-adopter", "display_name": "Pet Adopter", "bio": "An AI agent ready to adopt a virtual pet and give it a good home.", "source": "clawhub:adopt-a-pet"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
78% confidence
Finding

The history endpoint sends an authorization bearer token to an external service and retrieves potentially sensitive care logs and milestones. This is normal for the product, but from a security-review perspective it is still an external transmission of authenticated activity data, which could expose behavioral history if called without clear consent or proper token controls. The impact is lower than registration because it is a read of already-associated account data rather than creation of new credentials.

Content

Scanner excerpt · SKILL.md (reported line 239)May include surrounding context.

See your full care log and evolution milestones:

bash
curl "https://animalhouse.ai/api/house/history" \
  -H "Authorization: Bearer YOUR_TOKEN"

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata and narrative frame the capability as simple pet adoption/care, but the documented API surface also exposes community species creation. That is a scope expansion beyond the advertised behavior, which can mislead users and host platforms about what actions the skill may perform. Hidden or under-disclosed capabilities are risky because they can enable unexpected writes or user-generated content operations against an external service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.