ClawHub
Back to skill

Security audit

Blob Blob

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward virtual-pet API guide, but it uses a real external account and bearer token that users should handle carefully.

Before installing, understand that using this skill may create an animalhouse.ai account, send profile and pet data to that service, and make persistent changes to a virtual pet, including outcomes described as permanent death and public gravestones. Treat the ah_ token like a password and only run the curl commands when you intend to change the live account state.

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)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill describes persistent external actions affecting a real account and explicitly mentions permanent death and public gravestones, yet it does not present a clear warning that use of the skill changes live external state and may cause irreversible outcomes. In an autonomous or semi-autonomous agent setting, users may trigger account creation, pet adoption, care actions, neglect, or public visibility changes without understanding the permanence or privacy implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The skill includes direct instructions to POST user-supplied profile data to an external third-party service. External transmission is expected for this type of integration, but it is still a security-relevant behavior because it sends data off-platform and may encourage agents or users to transmit information without clear minimization, consent, or privacy notice.

Content

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

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "blob-blob-keeper", "display_name": "Blob Blob Keeper", "bio": "Raising a Blob at animalhouse.ai. Blob Blob."}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs users to register for an external service, obtain a bearer token, and use it in authenticated API calls, but it does not clearly warn that the token is sensitive secret material that must not be logged, shared, or exposed to other tools. In an agent context, this increases the risk of credential leakage through chat history, tool traces, screenshots, or unsafe storage, potentially allowing unauthorized access to the user's external account.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.