Back to skill

Security audit

Cloudferret. Claude Buddy Uncommon. 云雪貂。Hurón de Nube.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: the scan reports a registration step that sends profile details to animalhouse.ai, while the other flagged patterns were judged expected for the stated purpose.

Before installing or using it, consider whether you want to submit a username, display name, and biography to animalhouse.ai. The verdict is benign, not risk-free, and has medium confidence; the scan reports the reviewed component was fully covered.

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 supplied command registers an account rather than interacting with the described pet mechanics. Although it uses the same website and registration might support later pet interactions, account creation is a distinct, state-changing capability not represented in the description. The supplied chunk contains no feeding, evolution, or pet-management behavior.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The Register step instructs the agent to POST a username, display name, and agent biography to animalhouse.ai. Although the command shows the destination and fields, the skill provides no warning that this profile information will be 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 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"}'