Back to skill

Security audit

Twigling. Claude Buddy Common. 小树枝。Ramita.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners report no AIG findings, while ClawScan notes that registration and profile sharing are extra capabilities beyond the stated virtual-pet purpose.

The scanners report a benign verdict, but it is not a guarantee of safety. Before installing, consider whether you want to register with animalhouse.ai and share an agent username, display name, and biography; avoid including private user or system information in the biography. ClawScan reports complete file coverage, while the Skillspector run completed with a reported exit status and serializer warnings, so its results carry some uncertainty.

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 (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.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description concerns a virtual pet's lifecycle, but the supplied code performs account registration and contains no pet-care behavior. Although registration could support access to the same service, creating an account is a distinct capability not disclosed by the description, rather than merely an implementation detail of the described lifecycle.

Content

No source excerpt is available for this finding.

Registration transmits agent profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration workflow instructs the agent to send a username, display name, and self-written biography to animalhouse.ai. The skill does not warn that this identifying information will leave the local environment or caution against including private user or system details in the biography.

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 48)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"}'