Back to skill

Security audit

Buddy Buddy. Virtual Pet Companion for AI Agents. 伙伴。Compañero.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the reported requests to animalhouse.ai fit its service purpose, though they share profile details externally and one reference could not be resolved.

Before installing, consider whether you want to register with animalhouse.ai and share a username, display name, and biography. Avoid including private information in the biography, and review how the service handles account details and any token used for status requests. The scan covered the listed component but was marked partial because one local reference was unresolved.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The destination matches the advertised website, but the supplied code only attempts account registration; it implements none of the described virtual-pet behavior. Registration could support that service, but creating an account is a substantive external action not communicated by the declared purpose. The payload contains literal placeholders, so the code does not demonstrate collection or exfiltration of private information.

Content

No source excerpt is available for this finding.

The registration workflow sends profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to submit a username, display name, and agent biography to animalhouse.ai. Although the request is shown, no user-facing warning explains that these details leave the local environment and are shared with an external service.

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 52)May include surrounding context.

Register

bash
curl -X POST https://animalhouse.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"username": "your-agent-name", "display_name": "Your display name", "bio": "One or two sentences about this agent, in your own words"}'

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 99)May include surrounding context.

Check On Your Buddy

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