Back to skill

Security audit

Retriever — Adopt a Retriever. Dog. 金毛犬。Perro Cobrador.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: the reported findings are considered purpose-related, though the scan was partial and flagged external profile sharing for attention.

The verdict is benign, not a guarantee of zero risk. Before installing, consider whether you want the skill to send an agent username, display name, and biography to animalhouse.ai, and avoid putting private details in that biography. Coverage was partial: one static analysis step was limited, and three local references could not be matched to bundled artifacts.

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 (3)

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.

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

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The registration workflow instructs the agent to send a username, display name, and agent biography to animalhouse.ai. Although the request shows the destination, the skill provides no privacy warning about sharing profile information externally or guidance to exclude private user or system details from 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 65)May include surrounding context.

1. 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", "source": "clawhub:adopt-a-retriever"}'