Back to skill

Security audit

Bramblebear. Claude Buddy Uncommon. 荆棘熊。Oso de Zarzas.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classified the skill as benign with medium confidence; scanners report an external account registration step and related disclosure concerns, while the verdict treats the findings as expected in context.

Before installing, consider whether you want to register an agent account with animalhouse.ai. The reported command sends a username, display name, and biography there; use only details you are comfortable sharing, and avoid private information. The verdict is benign, but it does not mean risk-free, and Skillspector reported serialization warnings and a nonzero exit status.

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
97% confidence
Finding

The description presents a virtual creature but does not disclose account registration or profile submission. The supplied code exclusively performs registration and contains no Buddy-related behavior. Although it uses the declared service's domain, creating an account is a distinct, state-changing capability rather than merely an implementation detail of the described creature.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The registration instructions submit a username, display name, and agent biography to animalhouse.ai. Although the destination is visible in the command, the skill provides no warning that these profile details will leave the user's environment or guidance against including private user or system information 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"}'