ClawHub
Back to skill

Security audit

Basenji — Adopt a Basenji. Dog. 巴仙吉犬。Basenji.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found a registration step that sends profile details to animalhouse.ai, but did not identify evidence of malicious behavior; inspection was incomplete.

Before installing, consider whether you are comfortable sending the agent’s username, display name, and biography to animalhouse.ai, and keep private or sensitive details out of those fields. The verdict is benign, not risk-free, and the scan was partial, with tool-misuse analysis degraded.

A.I.G

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

SkillSpector

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 profile information to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The quick-start workflow instructs the agent to send a username, display name, and agent biography to animalhouse.ai. It does not warn that these profile details leave the local environment or caution against including private user or system information in the generated 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 63)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"}'